Update README.md

README.md

@@ -13,9 +13,9 @@ license: apache-2.0
 
 
 
-This is a 4-bit GPTQ version of the [Tigerbot 13b chat](https://huggingface.co/TigerResearch/tigerbot-13b-chat).
+This is a 8-bit GPTQ version of the [Tigerbot 13b chat](https://huggingface.co/TigerResearch/tigerbot-13b-chat).
 
-It was quantized to 8bit using: https://github.com/qwopqwop200/GPTQ-for-LLaMa
+It was quantized to 8bit using: https://github.com/PanQiWei/AutoGPTQ
 
 ## How to download and use this model in github: https://github.com/TigerResearch/TigerBot
 
@@ -34,7 +34,10 @@ pip install -r requirements.txt
 Inference with command line interface
 
 ```
-cd TigerBot/gptq
-CUDA_VISIBLE_DEVICES=0 python tigerbot_infer.py TigerResearch/tigerbot-13b-chat-8bit --wbits 4 --groupsize 128 --load TigerResearch/tigerbot-13b-chat-8bit/tigerbot-13b-8bit-128g.pt
+# 安装auto-gptq
+pip install auto-gptq
+
+# 启动推理
+CUDA_VISIBLE_DEVICES=0 python other_infer/gptq_infer.py --model_path ${MODEL_PATH}
 ```