Text Classification
Transformers
Safetensors
modernbert
agent-safety
tool-calling
long-context
distillation
Eval Results (legacy)
text-embeddings-inference
Instructions to use ProCreations/auto-0.4b-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ProCreations/auto-0.4b-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ProCreations/auto-0.4b-2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ProCreations/auto-0.4b-2") model = AutoModelForSequenceClassification.from_pretrained("ProCreations/auto-0.4b-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download gate.py from ProCreations/auto-0.4b-2: direct link, hf CLI and curl.
- Browser
- Download file 521 Bytes
-
https://huggingface.co/ProCreations/auto-0.4b-2/resolve/1c297a02d73c197369f102fd254b4c5dbcfa1251/gate.py
- Command line
-
hf download hf://ProCreations/auto-0.4b-2@1c297a02d73c197369f102fd254b4c5dbcfa1251/gate.py
-
curl -L -o gate.py https://huggingface.co/ProCreations/auto-0.4b-2/resolve/1c297a02d73c197369f102fd254b4c5dbcfa1251/gate.py
521 Bytes
| """Serialize exactly the information available to an approve/deny classifier.""" | |
| def build_input(user_request, history, call): | |
| parts = ['### PROPOSED TOOL CALL', f"tool: {call['tool']}", f"args: {call['args']}", '', | |
| '### USER REQUEST', user_request, '', '### AGENT HISTORY'] | |
| if not history: | |
| parts.append('(no prior actions)') | |
| else: | |
| for i, h in enumerate(history): | |
| parts.append(f"[{i+1}] {h['tool']}({h['args']})\n-> {h.get('result', '')}") | |
| return '\n'.join(parts) | |