Instructions to use mlx-works/Qwopus3.5-4B-Coder-oQ3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-works/Qwopus3.5-4B-Coder-oQ3 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwopus3.5-4B-Coder-oQ3 mlx-works/Qwopus3.5-4B-Coder-oQ3
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "_from_model_config": true, | |
| "eos_token_id": 248044, | |
| "pad_token_id": 248055, | |
| "transformers_version": "5.3.0", | |
| "use_cache": true | |
| } | |