Instructions to use aruntemme/maya2-native-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use aruntemme/maya2-native-mlx-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download aruntemme/maya2-native-mlx-8bit --local-dir maya2-native-mlx-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download backbone/tokenizer.json from aruntemme/maya2-native-mlx-8bit: direct link, hf CLI and curl.
- Browser
- Download file 16.1 MB
-
https://huggingface.co/aruntemme/maya2-native-mlx-8bit/resolve/main/backbone/tokenizer.json
- Command line
-
hf download hf://aruntemme/maya2-native-mlx-8bit/backbone/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/aruntemme/maya2-native-mlx-8bit/resolve/main/backbone/tokenizer.json
16.1 MB
- Xet hash:
- 1328d48c9f9cc676acf30040515a7e3e64623b0f7e2fe54f191db3b91b139b99
- Size of remote file:
- 16.1 MB
- SHA256:
- 26c51f9b772f9084ed6bdeabc44b7c15397c12966bfa3e1c09b025e82f4fdbaf
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.