Translation
Transformers
Safetensors
ONNX
m2m_100
text2text-generation
nllb-200
nllb
quantization
int8
4-bit precision
nf4
bitsandbytes
transformers-js
multilingual
neural-machine-translation
meta
seq2seq
Instructions to use rudrakshrakeshzodage/nllb-200-distilled-600M-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rudrakshrakeshzodage/nllb-200-distilled-600M-fp16 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="rudrakshrakeshzodage/nllb-200-distilled-600M-fp16")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("rudrakshrakeshzodage/nllb-200-distilled-600M-fp16") model = AutoModelForSeq2SeqLM.from_pretrained("rudrakshrakeshzodage/nllb-200-distilled-600M-fp16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download graph_model_size_comparison.png from rudrakshrakeshzodage/nllb-200-distilled-600M-fp16: direct link, hf CLI and curl.
- Browser
- Download file 101 kB
-
https://huggingface.co/rudrakshrakeshzodage/nllb-200-distilled-600M-fp16/resolve/main/graph_model_size_comparison.png
- Command line
-
hf download hf://rudrakshrakeshzodage/nllb-200-distilled-600M-fp16/graph_model_size_comparison.png
-
curl -L -o graph_model_size_comparison.png https://huggingface.co/rudrakshrakeshzodage/nllb-200-distilled-600M-fp16/resolve/main/graph_model_size_comparison.png
101 kB

- Xet hash:
- eb7ba55fbe33e3006652b3b8e163c6e3672d1ae84b0340c955d78066b0af29d3
- Size of remote file:
- 101 kB
- SHA256:
- e18b48118a6de7bb66cb01014dacba5c50fe4209a507233c7d4537d687e25bcf
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.