Instructions to use calebboud/vicuna with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use calebboud/vicuna with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("calebboud/vicuna", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download params_shard_103.bin from calebboud/vicuna: direct link, hf CLI and curl.
- Browser
- Download file 32 MB
-
https://huggingface.co/calebboud/vicuna/resolve/main/params_shard_103.bin
- Command line
-
hf download hf://calebboud/vicuna/params_shard_103.bin
-
curl -L -o params_shard_103.bin https://huggingface.co/calebboud/vicuna/resolve/main/params_shard_103.bin
32 MB
- Xet hash:
- faf7f8b984fe189a3b6dccc1a3488c920983b4a81eec1b87d62d5f91dd6786f7
- Size of remote file:
- 32 MB
- SHA256:
- 809a2ac505548fe74f1d79f2bb7e9f5de337ed3da761ae8a7ec49c9713102e97
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.