{ "created_at": "2026-08-15T01:04:29-0700", "files_copied": [ { "kind": "file-copy", "name": "README.md", "size_bytes": 81 }, { "kind": "file-copy", "name": "chat_template.jinja", "size_bytes": 8952 }, { "kind": "file-copy", "name": "config.json", "size_bytes": 4098 }, { "kind": "file-copy", "name": "generation_config.json", "size_bytes": 202 }, { "kind": "file-copy", "name": "model.safetensors.index.json", "size_bytes": 189789 }, { "kind": "file-copy", "name": "mtplx_runtime.json", "size_bytes": 4899 }, { "kind": "file-copy", "name": "tokenizer.json", "size_bytes": 19989325 }, { "kind": "file-copy", "name": "tokenizer_config.json", "size_bytes": 1161 } ], "output_path": "~/.mtplx/models/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "policy": "convert bf16 floating tensors to fp16; preserve packed integer/quantized tensors", "repo_id": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "safetensors": [ { "converted_bf16_to_fp16": 212, "name": "model-00001-of-00006.safetensors", "output_sha256": "9491f84a467c35baefa3979344bf5b5f6f88b6e3f996ffdecf998ae579b32ceb", "output_size_bytes": 5305469113, "preserved": 78, "source_sha256": "a11adc73146b142e77349999f67d5d13c031ff2bbafed0837388c1b6e48d4836", "source_size_bytes": 5305469313, "tensor_count": 290, "tensors": [ { "converted": true, "name": "language_model.model.embed_tokens.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 248320, 80 ] }, { "converted": true, "name": "language_model.model.embed_tokens.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 248320, 80 ] }, { "converted": false, "name": "language_model.model.embed_tokens.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 248320, 1280 ] }, { "converted": true, "name": "language_model.model.layers.0.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.0.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.0.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.0.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.0.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.0.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.0.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.0.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.0.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.0.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.0.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.0.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.0.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.0.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.0.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.0.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.0.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.1.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.1.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.1.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.1.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.1.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.1.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.1.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.1.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.1.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.1.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.1.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.1.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.1.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.1.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.1.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.1.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.1.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.2.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.2.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.2.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.2.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.2.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.2.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.2.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.2.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.2.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.2.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.2.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.2.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.2.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.2.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.2.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.2.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.2.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.3.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.3.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.3.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.3.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.3.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.3.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.3.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.3.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.3.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.3.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.3.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.3.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.3.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.3.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.3.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.3.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.4.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.4.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.4.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.4.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.4.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.4.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.4.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.4.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.4.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.4.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.4.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.4.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.4.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.4.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.4.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.4.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.4.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.5.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.5.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.5.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.5.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.5.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.5.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.5.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.5.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.5.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.5.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.5.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.5.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.5.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.5.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.5.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.5.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.5.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.6.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.6.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.6.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.6.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.6.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.6.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.6.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.6.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.6.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.6.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.6.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.6.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.6.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.6.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.6.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.6.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.6.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.7.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.7.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.7.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.7.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.7.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.7.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.7.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.7.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.7.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.7.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.7.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.7.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.7.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.7.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.7.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.7.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.8.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.8.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.8.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.8.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.8.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.8.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.8.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.8.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.8.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.8.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.8.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.8.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.8.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.8.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.8.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.8.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.8.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.9.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.9.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.9.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.9.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.9.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.9.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.9.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.9.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.9.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.9.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.9.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.9.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.9.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.9.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] } ] }, { "converted_bf16_to_fp16": 276, "name": "model-00002-of-00006.safetensors", "output_sha256": "469ecd6059833f765705e6107ff25465749e6029fc1949c02bbdd40b053d961c", "output_size_bytes": 5354102394, "preserved": 102, "source_sha256": "bd95f804980c5e79e212abe6e674020a30f24674780a92cb101dd9971484c6d0", "source_size_bytes": 5354102628, "tensor_count": 378, "tensors": [ { "converted": true, "name": "language_model.model.layers.10.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.10.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.10.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.10.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.10.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.10.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.10.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.10.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.10.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.10.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.10.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.10.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.10.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.10.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.10.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.10.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.10.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.11.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.11.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.11.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.11.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.11.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.11.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.11.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.11.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.11.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.11.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.11.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.11.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.11.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.11.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.11.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.11.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.12.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.12.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.12.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.12.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.12.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.12.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.12.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.12.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.12.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.12.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.12.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.12.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.12.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.12.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.12.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.12.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.12.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.13.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.13.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.13.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.13.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.13.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.13.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.13.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.13.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.13.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.13.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.13.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.13.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.13.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.13.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.13.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.13.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.13.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.14.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.14.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.14.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.14.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.14.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.14.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.14.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.14.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.14.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.14.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.14.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.14.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.14.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.14.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.14.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.14.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.14.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.15.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.15.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.15.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.15.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.15.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.15.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.15.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.15.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.15.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.15.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.15.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.15.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.15.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.15.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.15.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.15.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.16.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.16.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.16.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.16.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.16.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.16.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.16.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.16.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.16.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.16.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.16.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.16.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.16.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.16.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.16.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.16.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.16.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.17.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.17.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.17.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.17.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.17.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.17.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.17.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.17.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.17.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.17.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.17.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.17.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.17.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.17.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.17.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.17.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.17.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.18.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.18.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.18.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.18.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.18.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.18.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.18.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.18.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.18.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.18.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.18.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.18.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.18.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.18.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.18.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.18.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.18.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.19.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.19.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.19.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.19.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.19.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.19.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.19.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.19.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.19.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.19.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.19.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.19.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.19.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.19.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.19.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.19.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.20.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.20.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.20.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.20.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.20.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.20.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.20.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.20.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.20.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.20.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.20.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.20.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.20.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.20.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.20.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.20.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.20.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.21.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.21.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.21.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.21.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.21.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.21.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.21.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.21.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.21.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.21.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.21.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.21.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.21.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.21.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.21.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.21.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.21.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.22.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.22.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.22.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.22.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.22.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.22.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.22.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.22.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.22.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.22.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.22.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.22.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.22.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.22.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.22.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.22.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.22.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.9.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.9.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.9.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] } ] }, { "converted_bf16_to_fp16": 282, "name": "model-00003-of-00006.safetensors", "output_sha256": "6f26eca9788a48024c03c9755c1e2b9de90d38bdfbdf71a762d089f226696b2a", "output_size_bytes": 5337392740, "preserved": 104, "source_sha256": "91e3f7cc9fadd3599ebce87a9f8e8a4ab6d05f595a79da94868fa96c2d868b8e", "source_size_bytes": 5337392986, "tensor_count": 386, "tensors": [ { "converted": true, "name": "language_model.model.layers.23.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.23.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.23.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.23.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.23.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.23.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.23.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.23.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.23.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.23.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.23.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.23.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.23.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.23.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.23.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.23.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.24.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.24.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.24.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.24.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.24.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.24.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.24.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.24.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.24.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.24.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.24.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.24.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.24.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.24.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.24.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.24.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.24.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.25.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.25.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.25.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.25.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.25.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.25.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.25.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.25.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.25.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.25.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.25.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.25.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.25.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.25.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.25.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.25.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.25.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.26.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.26.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.26.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.26.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.26.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.26.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.26.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.26.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.26.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.26.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.26.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.26.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.26.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.26.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.26.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.26.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.26.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.27.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.27.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.27.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.27.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.27.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.27.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.27.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.27.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.27.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.27.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.27.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.27.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.27.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.27.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.27.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.27.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.28.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.28.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.28.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.28.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.28.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.28.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.28.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.28.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.28.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.28.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.28.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.28.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.28.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.28.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.28.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.28.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.28.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.29.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.29.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.29.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.29.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.29.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.29.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.29.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.29.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.29.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.29.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.29.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.29.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.29.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.29.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.29.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.29.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.29.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.30.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.30.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.30.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.30.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.30.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.30.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.30.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.30.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.30.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.30.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.30.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.30.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.30.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.30.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.30.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.30.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.30.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.31.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.31.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.31.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.31.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.31.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.31.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.31.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.31.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.31.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.31.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.31.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.31.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.31.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.31.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.31.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.31.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.32.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.32.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.32.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.32.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.32.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.32.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.32.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.32.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.32.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.32.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.32.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.32.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.32.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.32.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.32.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.32.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.32.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.33.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.33.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.33.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.33.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.33.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.33.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.33.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.33.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.33.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.33.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.33.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.33.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.33.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.33.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.33.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.33.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.33.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.34.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.34.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.34.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.34.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.34.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.34.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.34.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.34.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.34.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.34.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.34.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.34.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.34.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.34.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.34.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.34.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.34.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.35.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.35.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.35.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.35.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.35.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.35.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.35.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.35.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.35.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.35.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.35.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.35.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.35.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.35.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.35.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.35.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.36.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.36.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.36.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.36.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] } ] }, { "converted_bf16_to_fp16": 278, "name": "model-00004-of-00006.safetensors", "output_sha256": "25ecb3a3802a1e942794fd6045d9fa2f74cafa03a4ebc3d504513df725000c38", "output_size_bytes": 5292846872, "preserved": 102, "source_sha256": "ae6fee0e32edbf973e614ac040ad0f853df23f8c33bf97cadb4c168ef9a887a2", "source_size_bytes": 5292847128, "tensor_count": 380, "tensors": [ { "converted": true, "name": "language_model.model.layers.36.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.36.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.36.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.36.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.36.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.36.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.36.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.36.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.36.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.36.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.36.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.36.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.36.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.37.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.37.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.37.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.37.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.37.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.37.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.37.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.37.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.37.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.37.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.37.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.37.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.37.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.37.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.37.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.37.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.37.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.38.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.38.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.38.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.38.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.38.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.38.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.38.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.38.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.38.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.38.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.38.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.38.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.38.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.38.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.38.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.38.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.38.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.39.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.39.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.39.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.39.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.39.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.39.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.39.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.39.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.39.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.39.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.39.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.39.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.39.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.39.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.39.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.39.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.40.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.40.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.40.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.40.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.40.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.40.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.40.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.40.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.40.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.40.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.40.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.40.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.40.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.40.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.40.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.40.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.40.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.41.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.41.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.41.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.41.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.41.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.41.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.41.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.41.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.41.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.41.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.41.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.41.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.41.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.41.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.41.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.41.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.41.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.42.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.42.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.42.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.42.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.42.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.42.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.42.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.42.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.42.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.42.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.42.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.42.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.42.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.42.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.42.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.42.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.42.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.43.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.43.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.43.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.43.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.43.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.43.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.43.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.43.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.43.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.43.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.43.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.43.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.43.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.43.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.43.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.43.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.44.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.44.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.44.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.44.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.44.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.44.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.44.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.44.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.44.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.44.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.44.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.44.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.44.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.44.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.44.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.44.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.44.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.45.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.45.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.45.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.45.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.45.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.45.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.45.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.45.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.45.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.45.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.45.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.45.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.45.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.45.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.45.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.45.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.45.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.46.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.46.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.46.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.46.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.46.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.46.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.46.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.46.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.46.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.46.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.46.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.46.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.46.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.46.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.46.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.46.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.46.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.47.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.47.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.47.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.47.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.47.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.47.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.47.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.47.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.47.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.47.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.47.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.47.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.47.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.47.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.47.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.47.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.48.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.48.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.48.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.48.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.48.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.48.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.48.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.48.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.48.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.48.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.48.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.48.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.48.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.48.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.48.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.48.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.48.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.49.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.49.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.49.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.49.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.49.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.49.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.49.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.49.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] } ] }, { "converted_bf16_to_fp16": 276, "name": "model-00005-of-00006.safetensors", "output_sha256": "788eea30868a2e142aa182b5370c9d299701f04b796756894bbb044d5c9a8893", "output_size_bytes": 5354102367, "preserved": 102, "source_sha256": "c1735ac9c3d6cba8127b5c00a28576f0825d874a7f09911dc7bad5027a8747eb", "source_size_bytes": 5354102635, "tensor_count": 378, "tensors": [ { "converted": true, "name": "language_model.model.layers.49.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.49.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.49.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.49.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.49.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.49.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.49.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.49.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.49.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.50.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.50.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.50.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.50.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.50.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.50.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.50.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.50.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.50.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.50.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.50.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.50.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.50.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.50.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.50.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.50.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.50.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.51.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.51.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.51.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.51.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.51.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.51.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.51.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.51.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.51.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.51.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.51.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.51.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.51.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.51.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.51.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.51.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.52.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.52.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.52.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.52.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.52.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.52.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.52.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.52.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.52.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.52.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.52.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.52.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.52.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.52.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.52.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.52.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.52.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.53.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.53.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.53.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.53.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.53.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.53.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.53.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.53.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.53.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.53.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.53.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.53.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.53.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.53.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.53.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.53.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.53.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.54.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.54.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.54.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.54.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.54.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.54.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.54.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.54.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.54.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.54.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.54.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.54.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.54.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.54.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.54.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.54.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.54.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.55.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.55.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.55.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.55.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.55.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.55.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.55.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.55.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.55.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.55.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.55.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.55.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.55.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.55.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.55.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.55.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.56.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.56.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.56.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.56.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.56.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.56.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.56.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.56.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.56.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.56.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.56.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.56.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.56.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.56.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.56.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.56.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.56.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.57.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.57.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.57.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.57.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.57.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.57.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.57.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.57.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.57.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.57.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.57.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.57.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.57.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.57.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.57.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.57.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.57.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.58.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.58.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.58.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.58.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.58.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.58.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.58.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.58.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.58.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.58.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.58.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.58.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.58.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.58.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.58.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.58.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.58.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.59.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.59.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.59.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.59.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.59.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.59.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.59.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.59.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.59.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.59.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.59.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.59.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.59.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.59.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.59.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.59.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.60.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.60.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.60.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.60.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.60.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.60.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.60.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.60.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.60.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.60.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.60.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.60.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.60.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.60.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.60.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.60.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.60.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.61.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.61.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.61.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.61.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.61.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.61.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.61.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.61.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.61.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.61.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.61.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.61.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.61.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.61.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.61.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.61.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.61.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.62.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.A_log", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.conv1d.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 4, 1 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.dt_bias", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.in_proj_a.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.in_proj_a.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.62.linear_attn.in_proj_a.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.in_proj_b.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.in_proj_b.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 48, 80 ] }, { "converted": false, "name": "language_model.model.layers.62.linear_attn.in_proj_b.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 48, 1280 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.in_proj_qkv.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.in_proj_qkv.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 10240, 80 ] }, { "converted": false, "name": "language_model.model.layers.62.linear_attn.in_proj_qkv.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 10240, 1280 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.in_proj_z.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.in_proj_z.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 6144, 80 ] }, { "converted": false, "name": "language_model.model.layers.62.linear_attn.in_proj_z.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 6144, 1280 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 128 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.out_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.62.linear_attn.out_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.62.linear_attn.out_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.62.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.62.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.62.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.62.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] } ] }, { "converted_bf16_to_fp16": 25, "name": "model-00006-of-00006.safetensors", "output_sha256": "486e14f0c4c0fbdc10649dcf54861986d6ad5892965bffe3b8bc28ba64c80beb", "output_size_bytes": 1935805708, "preserved": 10, "source_sha256": "2452a44eddf64d0cd964245b37f47f3b406c9c397b0eb5fd605bfb9c2f8825f9", "source_size_bytes": 1935805825, "tensor_count": 35, "tensors": [ { "converted": true, "name": "language_model.lm_head.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 248320, 80 ] }, { "converted": true, "name": "language_model.lm_head.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 248320, 80 ] }, { "converted": false, "name": "language_model.lm_head.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 248320, 1280 ] }, { "converted": true, "name": "language_model.model.layers.62.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.62.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.62.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.62.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.62.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.62.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.63.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.63.mlp.down_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": true, "name": "language_model.model.layers.63.mlp.down_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 272 ] }, { "converted": false, "name": "language_model.model.layers.63.mlp.down_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 4352 ] }, { "converted": true, "name": "language_model.model.layers.63.mlp.gate_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.63.mlp.gate_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.63.mlp.gate_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.63.mlp.up_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": true, "name": "language_model.model.layers.63.mlp.up_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 80 ] }, { "converted": false, "name": "language_model.model.layers.63.mlp.up_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 17408, 1280 ] }, { "converted": true, "name": "language_model.model.layers.63.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.k_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.k_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.63.self_attn.k_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.o_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.o_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 96 ] }, { "converted": false, "name": "language_model.model.layers.63.self_attn.o_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 5120, 1536 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.q_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.q_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 80 ] }, { "converted": false, "name": "language_model.model.layers.63.self_attn.q_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 12288, 1280 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.v_proj.biases", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": true, "name": "language_model.model.layers.63.self_attn.v_proj.scales", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 80 ] }, { "converted": false, "name": "language_model.model.layers.63.self_attn.v_proj.weight", "new_dtype": "uint32", "old_dtype": "uint32", "shape": [ 1024, 1280 ] }, { "converted": true, "name": "language_model.model.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] } ] }, { "converted_bf16_to_fp16": 15, "name": "mtp.safetensors", "output_sha256": "6ee6f23703190a9468baab968205b4256cee628cfcf32cd79e8592524a8fdbc7", "output_size_bytes": 849400388, "preserved": 0, "source_sha256": "4468f39621de68a19ffd0bcb2e2e2f352205def7436a625b3427e3752866c287", "source_size_bytes": 849400403, "tensor_count": 15, "tensors": [ { "converted": true, "name": "mtp.fc.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 10240 ] }, { "converted": true, "name": "mtp.layers.0.input_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "mtp.layers.0.mlp.down_proj.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 17408 ] }, { "converted": true, "name": "mtp.layers.0.mlp.gate_proj.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 5120 ] }, { "converted": true, "name": "mtp.layers.0.mlp.up_proj.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 17408, 5120 ] }, { "converted": true, "name": "mtp.layers.0.post_attention_layernorm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "mtp.layers.0.self_attn.k_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "mtp.layers.0.self_attn.k_proj.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 5120 ] }, { "converted": true, "name": "mtp.layers.0.self_attn.o_proj.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120, 6144 ] }, { "converted": true, "name": "mtp.layers.0.self_attn.q_norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 256 ] }, { "converted": true, "name": "mtp.layers.0.self_attn.q_proj.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 12288, 5120 ] }, { "converted": true, "name": "mtp.layers.0.self_attn.v_proj.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 1024, 5120 ] }, { "converted": true, "name": "mtp.norm.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "mtp.pre_fc_norm_embedding.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] }, { "converted": true, "name": "mtp.pre_fc_norm_hidden.weight", "new_dtype": "float16", "old_dtype": "bfloat16", "shape": [ 5120 ] } ] } ], "source_path": "~/.mtplx/models/Qwen3.8-27B-MTPLX-Optimized-Quality", "source_repo": null, "summary": { "converted_bf16_to_fp16": 1364, "preserved": 498, "shards": 7, "tensors_total": 1862 } }