Instructions to use codesage/codesage-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codesage/codesage-base with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import CodeSage model = CodeSage.from_pretrained("codesage/codesage-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from codesage/codesage-base: direct link, hf CLI and curl.
- Browser
- Download file 119 Bytes
-
https://huggingface.co/codesage/codesage-base/resolve/main/generation_config.json
- Command line
-
hf download hf://codesage/codesage-base/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/codesage/codesage-base/resolve/main/generation_config.json
119 Bytes
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 50256, | |
| "eos_token_id": 50256, | |
| "transformers_version": "4.28.1" | |
| } | |