Instructions to use mlx-community/deepseek-coder-6.7b-base-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/deepseek-coder-6.7b-base-4bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir deepseek-coder-6.7b-base-4bit-mlx mlx-community/deepseek-coder-6.7b-base-4bit-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
can you convert DeepSeek-Coder-V2-Instruct to mlx?
#1
by kerfern - opened
hi there.
i am just trying to convert the DeepSeek-Coder-V2-Instruct to mlx. but seems lie it doesnt convert out of the box and get the error that
"ValueError: Model type deepseek_v2 not supported."
just wondering how you converted a deepseek coder model? And hoping that you can share it.
Thanks
Working on it :)
thanks man!
Most welcome!