Instructions to use ArthurZ/kev-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ArthurZ/kev-4b with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ArthurZ/kev-4b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from ArthurZ/kev-4b: direct link, hf CLI and curl.
- Browser
- Download file 1.13 kB
-
https://huggingface.co/ArthurZ/kev-4b/resolve/main/README.md
- Command line
-
hf download hf://ArthurZ/kev-4b/README.md
-
curl -L -o README.md https://huggingface.co/ArthurZ/kev-4b/resolve/main/README.md
1.13 kB
| license: apache-2.0 | |
| base_model: jaredpalmer/kev-4b | |
| library_name: transformers | |
| tags: | |
| - decision | |
| - systemone | |
| # jaredpalmer/kev-4b: decision files | |
| Chat template, settings and head of [jaredpalmer/kev-4b](https://huggingface.co/jaredpalmer/kev-4b) for `pipeline("decision")` | |
| ([transformers#49566](https://github.com/huggingface/transformers/pull/49566)). The backbone stays the original checkpoint. | |
| ```python | |
| from transformers import pipeline | |
| decide = pipeline("decision", model="jaredpalmer/kev-4b", decision_config="ArthurZ/kev-4b") | |
| decide({"state": "I was charged twice and want a refund.", "questions": {"refund": {"type": "noul", "instructions": "Is a refund requested?"}}}) | |
| ``` | |
| - `decision_template.jinja`: the chat template; `<|mark|>` marks the positions the head reads. | |
| - `decision_config.json`: temperatures and option order. | |
| - `decision_head/`: `KevDecisionHead`, converted from `head.pt` of the original. | |
| - `decision_test.json`: a request and the input ids that the original code builds for it, used by the tests. | |
| Derived from [jaredpalmer/kev-4b](https://huggingface.co/jaredpalmer/kev-4b) (Apache-2.0). | |