From 286b4cb8f4175865fd0736d36e032ad08ca7ad43 Mon Sep 17 00:00:00 2001 From: liushu <1554987494@qq.com> Date: Wed, 26 Apr 2023 20:02:46 +0800 Subject: [PATCH 1/2] add project --- PROJECT.md | 1 + 1 file changed, 1 insertion(+) diff --git a/PROJECT.md b/PROJECT.md index 14c9940..f5654a6 100644 --- a/PROJECT.md +++ b/PROJECT.md @@ -17,6 +17,7 @@ * [ChatGLM-web](https://github.com/NCZkevin/chatglm-web):基于FastAPI和Vue3搭建的ChatGLM演示网站(支持chatglm流式输出、前端调整模型参数、上下文选择、保存图片、知识库问答等功能) * [ChatGLM-6B-Engineering](https://github.com/LemonQu-GIT/ChatGLM-6B-Engineering):基于 ChatGLM-6B 后期调教,网络爬虫及 [Stable Diffusion](https://github.com/AUTOMATIC1111/stable-diffusion-webui) 实现的网络搜索及图片生成 * [ChatGLM-OpenAI-API](https://github.com/ninehills/chatglm-openai-api): 将 ChatGLM-6B 封装为 OpenAI API 风格,并通过 ngrok/cloudflare 对外提供服务,从而将 ChatGLM 快速集成到 OpenAI 的各种生态中。 +* [ChatSQL](https://github.com/yysirs/ChatSQL): 基于ChatGLM+SBERT实现NL2SQL本地化,并直接连接数据库查询数据返回结果,使得生成的SQL语句更具有实用性。 对 ChatGLM-6B 进行微调的开源项目: * [InstructGLM](https://github.com/yanqiangmiffy/InstructGLM):基于ChatGLM-6B进行指令学习,汇总开源中英文指令数据,基于Lora进行指令数据微调,开放了Alpaca、Belle微调后的Lora权重,修复web_demo重复问题 From 0903d2377f8c283175545471708f208f6e933e31 Mon Sep 17 00:00:00 2001 From: hwaking Date: Fri, 28 Apr 2023 14:51:48 +0800 Subject: [PATCH 2/2] Update web_demo2.py MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 当前MAX_BOXES与MAX_TURNS不生效导致单次对话不终止显存不断增加最后显存溢出问题,修改最大对话轮数和最大历史对话数量使其生效,逻辑为历史最大对话框记录轮数达到MAX_BOXES时截断历史对话为最近MAX_TURNS数。 --- web_demo2.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/web_demo2.py b/web_demo2.py index 226682e..ce976b3 100644 --- a/web_demo2.py +++ b/web_demo2.py @@ -28,6 +28,8 @@ def predict(input, max_length, top_p, temperature, history=None): with container: if len(history) > 0: + if len(history)>MAX_BOXES: + history = history[-MAX_TURNS:] for i, (query, response) in enumerate(history): message(query, avatar_style="big-smile", key=str(i) + "_user") message(response, avatar_style="bottts", key=str(i)) @@ -66,4 +68,4 @@ 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, max_length, top_p, temperature, st.session_state["state"]) \ No newline at end of file + st.session_state["state"] = predict(prompt_text, max_length, top_p, temperature, st.session_state["state"])