bnb-4 bit
Collection
A 4-bit quantized version models designed for fine-tuning. Demo: https://colab.research.google.com/drive/19UpFUjtbJoLua-4DMb1JKKwJAcvMyMHb
•
21 items
•
Updated
Mistral-7B-v0.1 - bnb 4bit
- Model creator: Mistral AI_
- Original model: Mistral-7B-v0.1
Description
This model is 4bit quantized version of Mistral-7B-v0.1 using bitsandbytes. It's designed for fine-tuning! The PAD token is set as UNK.
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model authors have turned it off explicitly.
Model tree for leliuga/Mistral-7B-v0.1-bnb-4bit
Base model
mistralai/Mistral-7B-v0.1