mirror of https://github.com/THUDM/ChatGLM-6B
				
				
				
			Merge branch 'main' of github.com:THUDM/ChatGLM-6B
						commit
						7836739311
					
				| 
						 | 
				
			
			@ -35,6 +35,7 @@ ChatGLM-6B 使用了和 ChatGPT 相似的技术,针对中文问答和对话进
 | 
			
		|||
* [bibliothecarius](https://github.com/coderabbit214/bibliothecarius):快速构建服务以集成您的本地数据和AI模型,支持ChatGLM等本地化模型接入。
 | 
			
		||||
* [闻达](https://github.com/l15y/wenda):大型语言模型调用平台,基于 ChatGLM-6B 实现了类 ChatPDF 功能
 | 
			
		||||
* [JittorLLMs](https://github.com/Jittor/JittorLLMs):最低3G显存或者没有显卡都可运行 ChatGLM-6B FP16, 支持Linux、windows、Mac部署
 | 
			
		||||
* [ChatGLM-Finetuning](https://github.com/liucongg/ChatGLM-Finetuning):基于ChatGLM-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning等,并进行实验效果对比。
 | 
			
		||||
 | 
			
		||||
以下是部分针对本项目的教程/文档:
 | 
			
		||||
* [Windows部署文档](https://github.com/ZhangErling/ChatGLM-6B/blob/main/deployment_windows.md)
 | 
			
		||||
| 
						 | 
				
			
			
 | 
			
		|||
							
								
								
									
										16
									
								
								web_demo2.py
								
								
								
								
							
							
						
						
									
										16
									
								
								web_demo2.py
								
								
								
								
							| 
						 | 
				
			
			@ -21,7 +21,7 @@ MAX_TURNS = 20
 | 
			
		|||
MAX_BOXES = MAX_TURNS * 2
 | 
			
		||||
 | 
			
		||||
 | 
			
		||||
def predict(input, history=None):
 | 
			
		||||
def predict(input, max_length, top_p, temperature, history=None):
 | 
			
		||||
    tokenizer, model = get_model()
 | 
			
		||||
    if history is None:
 | 
			
		||||
        history = []
 | 
			
		||||
| 
						 | 
				
			
			@ -35,7 +35,8 @@ def predict(input, history=None):
 | 
			
		|||
        message(input, avatar_style="big-smile", key=str(len(history)) + "_user")
 | 
			
		||||
        st.write("AI正在回复:")
 | 
			
		||||
        with st.empty():
 | 
			
		||||
            for response, history in model.stream_chat(tokenizer, input, history):
 | 
			
		||||
            for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
 | 
			
		||||
                                               temperature=temperature):
 | 
			
		||||
                query, response = history[-1]
 | 
			
		||||
                st.write(response)
 | 
			
		||||
 | 
			
		||||
| 
						 | 
				
			
			@ -49,6 +50,15 @@ prompt_text = st.text_area(label="用户命令输入",
 | 
			
		|||
            height = 100,
 | 
			
		||||
            placeholder="请在这儿输入您的命令")
 | 
			
		||||
 | 
			
		||||
max_length = st.sidebar.slider(
 | 
			
		||||
    'max_length', 0, 4096, 2048, step=1
 | 
			
		||||
)
 | 
			
		||||
top_p = st.sidebar.slider(
 | 
			
		||||
    'top_p', 0.0, 1.0, 0.6, step=0.01
 | 
			
		||||
)
 | 
			
		||||
temperature = st.sidebar.slider(
 | 
			
		||||
    'temperature', 0.0, 1.0, 0.95, step=0.01
 | 
			
		||||
)
 | 
			
		||||
 | 
			
		||||
if 'state' not in st.session_state:
 | 
			
		||||
    st.session_state['state'] = []
 | 
			
		||||
| 
						 | 
				
			
			@ -56,4 +66,4 @@ if 'state' not in st.session_state:
 | 
			
		|||
if st.button("发送", key="predict"):
 | 
			
		||||
    with st.spinner("AI正在思考,请稍等........"):
 | 
			
		||||
        # text generation
 | 
			
		||||
        st.session_state["state"] = predict(prompt_text, st.session_state["state"])
 | 
			
		||||
        st.session_state["state"] = predict(prompt_text, max_length, top_p, temperature, st.session_state["state"])
 | 
			
		||||
		Loading…
	
		Reference in New Issue