Instructions to use zerodegress/Index-Translate-2B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use zerodegress/Index-Translate-2B-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download zerodegress/Index-Translate-2B-MLX-4bit --local-dir Index-Translate-2B-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download generation_config.json from zerodegress/Index-Translate-2B-MLX-4bit: direct link, hf CLI and curl.
- Browser
- Download file 100 Bytes
-
https://huggingface.co/zerodegress/Index-Translate-2B-MLX-4bit/resolve/main/generation_config.json
- Command line
-
hf download hf://zerodegress/Index-Translate-2B-MLX-4bit/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/zerodegress/Index-Translate-2B-MLX-4bit/resolve/main/generation_config.json
100 Bytes
| { | |
| "eos_token_id": [ | |
| 248044, | |
| 248046 | |
| ], | |
| "pad_token_id": 248044, | |
| "bos_token_id": null | |
| } |