metadata

base_model: mistralai/Mistral-7B-Instruct-v0.1
license: apache-2.0
inference: false
model_creator: Mistral AI_
model_name: Mistral-7B-Instruct-v0.1
quantized_by: Leliuga
pipeline_tag: text-generation
arxiv: 2310.06825
tags:
  - mistral

Mistral-7B-Instruct-v0.1 - bnb 4bit

Model creator: Mistral AI_
Original model: Mistral-7B-Instruct-v0.1

Description

This model is 4bit quantized version of Mistral-7B-Instruct-v0.1 using bitsandbytes. It's designed for fine-tuning! The PAD token is set as UNK.