---
license: apache-2.0
---
<div style="width: 100%;">
    <img src="http://x-pai.algolet.com/bot/img/logo_core.png" alt="TigerBot" style="width: 20%; display: block; margin: auto;">
</div>
<p align="center">
<font face="黑体" color=orange size=5"> A cutting-edge foundation for your very own LLM. </font>
</p>
<p align="center">
   🌐 <a href="https://tigerbot.com/" target="_blank">TigerBot</a> • 🤗 <a href="https://huggingface.co/TigerResearch" target="_blank">Hugging Face</a>
</p>



This is a 4-bit GPTQ version of the [Tigerbot 7B sft](https://huggingface.co/TigerResearch/tigerbot-7b-sft).

It was quantized to 4bit using [GPTQ](https://github.com/TigerResearch/TigerBot/tree/main/gptq).

## How to download and use this model in [TigerBot](https://github.com/TigerResearch/TigerBot)

File `tigerbot-7b-4bit-128g.pt` can be loaded
with [GPTQ in TigerBot](https://github.com/TigerResearch/TigerBot/tree/main/gptq).
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

```
cd TigerBot/gptq
CUDA_VISIBLE_DEVICES=0 python tigerbot_infer.py TigerResearch/tigerbot-7b-sft-4bit-128g --wbits 4 --groupsize 128 --load tigerbot-7b-4bit-128g.pt
```