Instructions to use jartine/dolphin-2.5-mixtral-8x7b-llamafile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jartine/dolphin-2.5-mixtral-8x7b-llamafile with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jartine/dolphin-2.5-mixtral-8x7b-llamafile", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download dolphin-2.5-mixtral-8x7b.Q3_K_M.llamafile from jartine/dolphin-2.5-mixtral-8x7b-llamafile: direct link, hf CLI and curl.
- Browser
- Download file 20.4 GB
-
https://huggingface.co/jartine/dolphin-2.5-mixtral-8x7b-llamafile/resolve/main/dolphin-2.5-mixtral-8x7b.Q3_K_M.llamafile
- Command line
-
hf download hf://jartine/dolphin-2.5-mixtral-8x7b-llamafile/dolphin-2.5-mixtral-8x7b.Q3_K_M.llamafile
-
curl -L -o dolphin-2.5-mixtral-8x7b.Q3_K_M.llamafile https://huggingface.co/jartine/dolphin-2.5-mixtral-8x7b-llamafile/resolve/main/dolphin-2.5-mixtral-8x7b.Q3_K_M.llamafile
20.4 GB
- Xet hash:
- b9944de12c0471cea8a45af085ab3ef729baffded5861f44f1a8c531cb5a04d3
- Size of remote file:
- 20.4 GB
- SHA256:
- 069741480e8785eccaff028e052cd1af0135b68d7e5ce4ae18d6cf3240a4e0a3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.