Instructions to use sumo43/mistral-7b-2-L40 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sumo43/mistral-7b-2-L40 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sumo43/mistral-7b-2-L40", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download rank1.engine from sumo43/mistral-7b-2-L40: direct link, hf CLI and curl.
- Browser
- Download file 7.38 GB
-
https://huggingface.co/sumo43/mistral-7b-2-L40/resolve/main/rank1.engine
- Command line
-
hf download hf://sumo43/mistral-7b-2-L40/rank1.engine
-
curl -L -o rank1.engine https://huggingface.co/sumo43/mistral-7b-2-L40/resolve/main/rank1.engine
7.38 GB
- Xet hash:
- 51ceac31ecd05d32d99f42c9ffa776ee43bcd089dfd3327e5eae2d48fd10ce65
- Size of remote file:
- 7.38 GB
- SHA256:
- bd55edf6678f593b9119295423a29e3e7c60a32ddefff3d231a7e7466534621f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.