Update README.md

README.md

@@ -9,4 +9,18 @@ license: apache-2.0
 基础模型：华佗 GPT2-7B
 量化方法：int8 量化，使用 bitsandbytes 库
 模型大小：量化后约为 8GB，原模型大小为 26.8GB
-来源：百川模型支持
+来源：百川模型支持
+使用指南：
+```
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.generation.utils import GenerationConfig
+tokenizer = AutoTokenizer.from_pretrained("jiangchengchengNLP/huatuo-7b-sns8bits", use_fast=True, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("jiangchengchengNLP/huatuo-7b-sns8bits", device_map="auto", torch_dtype="auto", trust_remote_code=True)
+model.generation_config = GenerationConfig.from_pretrained("FreedomIntelligence/HuatuoGPT2-7B-4bits")
+messages = []
+messages.append({"role": "user", "content": "肚子疼怎么办？"})
+response = model.HuatuoChat(tokenizer, messages)
+print(response)
+
+```