Instructions to use nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-2Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-2Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir DeepSeek-Coder-V2-Instruct-mlx-2Bit nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-2Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "bos_token": { | |
| "content": "<|begin▁of▁sentence|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "<|end▁of▁sentence|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<|end▁of▁sentence|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |