对中文微调的模型参数进行了量化，方便以更少的计算资源运行。目前已经在Hugging Face上传了13B中文微调模型FlagAlpha/Llama2-Chinese-13b-Chat的4bit压缩版本FlagAlpha/Llama2-Chinese-13b-Chat-4bit，具体调用方式如下：

环境准备：

pip install git+https://github.com/PanQiWei/AutoGPTQ.git

from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM
model = AutoGPTQForCausalLM.from_quantized('FlagAlpha/Llama2-Chinese-13b-Chat-4bit', device="cuda:0")
tokenizer = AutoTokenizer.from_pretrained('FlagAlpha/Llama2-Chinese-13b-Chat-4bit',use_fast=False)
input_ids = tokenizer(['<s>Human: 怎么登上火星\n</s><s>Assistant: '], return_tensors="pt",add_special_tokens=False).input_ids.to('cuda')        
generate_input = {"input_ids":input_ids,"max_new_tokens":512,"do_sample":True,"top_k":50,"top_p":0.95,"temperature":0.3,"repetition_penalty":1.3,"eos_token_id":tokenizer.eos_token_id,"bos_token_id":tokenizer.bos_token_id,"pad_token_id":tokenizer.pad_token_id
}
generate_ids  = model.generate(**generate_input)
text = tokenizer.decode(generate_ids[0])
print(text)