Instructions to use ArthurZ/d3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ArthurZ/d3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="ArthurZ/d3")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ArthurZ/d3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download decision_head.json from ArthurZ/d3: direct link, hf CLI and curl.
- Browser
- Download file 366 Bytes
-
https://huggingface.co/ArthurZ/d3/resolve/main/decision_head.json
- Command line
-
hf download hf://ArthurZ/d3/decision_head.json
-
curl -L -o decision_head.json https://huggingface.co/ArthurZ/d3/resolve/main/decision_head.json
366 Bytes
| { | |
| "dtype": "bfloat16", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "model_type": "jev", | |
| "num_verbalizers": 255, | |
| "offsets": { | |
| "choice": 0, | |
| "noul": 0, | |
| "score": 0 | |
| }, | |
| "question_types": [ | |
| "noul", | |
| "choice", | |
| "score" | |
| ], | |
| "softcap": null, | |
| "transformers_version": "5.19.0.dev0", | |
| "transformers_weights": "model.safetensors" | |
| } | |