Instructions to use mlx-community/Mistral-7B-Instruct-v0.3-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Mistral-7B-Instruct-v0.3-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/Mistral-7B-Instruct-v0.3-8bit --local-dir Mistral-7B-Instruct-v0.3-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download tokenizer.model from mlx-community/Mistral-7B-Instruct-v0.3-8bit: direct link, hf CLI and curl.
- Browser
- Download file 587 kB
-
https://huggingface.co/mlx-community/Mistral-7B-Instruct-v0.3-8bit/resolve/main/tokenizer.model
- Command line
-
hf download hf://mlx-community/Mistral-7B-Instruct-v0.3-8bit/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/mlx-community/Mistral-7B-Instruct-v0.3-8bit/resolve/main/tokenizer.model
587 kB
- Xet hash:
- 70de076fa18896073beef6149fbfc8ac2a287bc510c1a6f422ca4b8538b7a952
- Size of remote file:
- 587 kB
- SHA256:
- 37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.