Instructions to use Fmuaddib/reka-flash-3-mlx-8Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Fmuaddib/reka-flash-3-mlx-8Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir reka-flash-3-mlx-8Bit Fmuaddib/reka-flash-3-mlx-8Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Upload tokenizer.json with huggingface_hub
Browse files- tokenizer.json +0 -0
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|