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
Phi-3-mini-128k-instruct - bnb 4bit
- Model creator: Microsoft
- Original model: Phi-3-mini-128k-instruct
Description
This model is 4bit quantized version of Phi-3-mini-128k-instruct using bitsandbytes. It's designed for fine-tuning! The PAD token is set as "<|endoftext|>".
- Downloads last month
- 43
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/Phi-3-mini-128k-instruct-bnb-4bit
Base model
microsoft/Phi-3-mini-128k-instruct