MLX
Safetensors
qwen2
Merge
mergekit
lazymergekit
maywell/Qwen2-7B-Multilingual-RP
Weyaxi/Einstein-v7-Qwen2-7B
mlx-my-repo
4-bit precision
Instructions to use fengpeisheng1/BerryBase-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use fengpeisheng1/BerryBase-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download fengpeisheng1/BerryBase-mlx-4Bit --local-dir BerryBase-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download tokenizer.json from fengpeisheng1/BerryBase-mlx-4Bit: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/fengpeisheng1/BerryBase-mlx-4Bit/resolve/main/tokenizer.json
- Command line
-
hf download hf://fengpeisheng1/BerryBase-mlx-4Bit/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/fengpeisheng1/BerryBase-mlx-4Bit/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 31d19fffde1c78260dd5b32b98e51dd8adefae216e6eefbcb299f56f4b977337
- Size of remote file:
- 11.4 MB
- SHA256:
- bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.