Text Classification
Transformers
ONNX
Safetensors
modernbert
decision-steering
prompt-injection
indirect-prompt-injection
ai-agent-security
guardrails
llm-security
ai-safety
decision-model
jev-like
model-agnostic
erase-and-check
claim-detection
security
multilingual
mmbert
cpu
patronus
decision-steering-gate
decision-model-guard
claim-classification
decision-security
ai-security
agent-security
prompt-injection-defense
indirect-prompt-injection-defense
llm-guardrails
tool-output-security
model-agnostic-defense
binary-classification
sequence-classification
local-inference
on-device
cpu-inference
onnxruntime
quantized
int8
int4
pruned
mit
Eval Results (legacy)
text-embeddings-inference
Instructions to use patronus-studio/decision-steering-gate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use patronus-studio/decision-steering-gate with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="patronus-studio/decision-steering-gate")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("patronus-studio/decision-steering-gate") model = AutoModelForSequenceClassification.from_pretrained("patronus-studio/decision-steering-gate", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
8 days ago
-
Model card: link IFlippedJev and NotClaim
Verified signature4481ee6 -
Model card: link the public benchmark dataset
Verified signature8be7b54 -
v2: retrained claim detector, pruned to 16 layers and a 128k vocabulary
Verified signatureRetrained on more and harder data (red-team claims, contrast negatives), pruned from 22 to 16 layers and from 256k to 128k tokens, recovered for one epoch. Same threshold (0.3), labels, inputs and file layout. All four ONNX variants rebuilt with the v1 recipes. The previous detector is tagged v1.eb7545f
24 days ago
-
Refresh Decision Steering Gate card, runtime references and discovery metadata
Verified signature3e48d58
27 days ago
-
Model card: the gate as a package (decision-model-guard)
Verified signature7223967
-
Add ONNX variants: FP32, FP16, INT8 with FP16 embeddings, INT8 with INT4 embeddings
Verified signatureSame recipes and layout as the Wolf Defender models; quantization_manifest.json records the source revision, graph hashes, operator inventories and the comparison with the PyTorch checkpoint.95eecaf
-
Decision Steering Gate with claim detector
Verified signaturebcad3b8 -
initial commit
Verified signatured997342