TigerResearch/tigerbot-7b-chat-4bit

A cutting-edge foundation for your very own LLM.

This is a 4-bit GPTQ version of the Tigerbot 7b chat.

It was quantized to 4bit using: https://github.com/PanQiWei/AutoGPTQ

How to download and use this model in github: https://github.com/TigerResearch/TigerBot

Here are commands to clone the TigerBot and install.

conda create --name tigerbot python=3.8
conda activate tigerbot
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia

git clone https://github.com/TigerResearch/TigerBot
cd TigerBot
pip install -r requirements.txt

Inference with command line interface

infer with auto-gptq

# 安装auto-gptq
pip install auto-gptq

# 启动推理
CUDA_VISIBLE_DEVICES=0 python other_infer/gptq_infer.py --model_path TigerResearch/tigerbot-7b-chat-4bit

infer with exllama

# 安装exllama_lib
pip install exllama_lib@git+https://github.com/taprosoft/exllama.git

# 启动推理
CUDA_VISIBLE_DEVICES=0 python other_infer/exllama_infer.py --model_path TigerResearch/tigerbot-7b-chat-4bit