|
Download README.md from subhash4face/agentic-ai-routing-task-classifier: direct link, hf CLI and curl.
- Browser
- Download file 725 Bytes
-
https://huggingface.co/subhash4face/agentic-ai-routing-task-classifier/resolve/main/README.md
- Command line
-
hf download hf://subhash4face/agentic-ai-routing-task-classifier/README.md
-
curl -L -o README.md https://huggingface.co/subhash4face/agentic-ai-routing-task-classifier/resolve/main/README.md
725 Bytes
| # Agentic AI Routing Classifier (20260906_020241) | |
| Fine-tuned **microsoft/deberta-v3-small** to route a user prompt into one of 11 task types. | |
| ## Classes | |
| QA, Summary, Coding, Reasoning, Agentic, Creative, Translation, Classification, Extraction, Long-context, Fast/simple | |
| ## Bundle contents | |
| - `model.safetensors` / `config.json` -> weights + config (includes id2label/label2id) | |
| - `tokenizer.json` / `tokenizer_config.json` -> DeBERTa tokenizer | |
| - `training_args.json` -> training hyper-parameters | |
| - `metrics.json` -> held-out eval metrics + confusion matrix | |
| - `dataset_manifest.json`-> dataset + leakage stats | |
| - `requirements.txt` -> pinned environment | |
| - `route_prompt.py` -> standalone inference script | |