├── .gitignore ├── LICENSE ├── README.md ├── chatglm_api.py ├── chatglm_api_macos.py ├── cli_demo.py ├── requirements.txt ├── resources ├── cli-demo.png └── web-demo.png └── web_demo.py /.gitignore: -------------------------------------------------------------------------------- 1 | .idea/ -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # ChatGLM-6B API 2 | 3 | ## 介绍 4 | 5 | 基于可私有部署的 ChatGLM-6B 对话语言模型，使用 fastapi 实现本地 API 部署，并在 web_demo 中提供基于 gradio 的 web 应用案例。 6 | 7 | > ChatGLM-6B 是一个开源的、支持中英双语的对话语言模型，基于 [General Language Model (GLM)](https://github.com/THUDM/GLM) 架构，具有 62 亿参数。结合模型量化技术，用户可以在消费级的显卡上进行本地部署（INT4 量化级别下最低只需 6GB 显存）。 8 | ChatGLM-6B 使用了和 ChatGPT 相似的技术，针对中文问答和对话进行了优化。经过约 1T 标识符的中英双语训练，辅以监督微调、反馈自助、人类反馈强化学习等技术的加持，62 亿参数的 ChatGLM-6B 已经能生成相当符合人类偏好的回答。 9 | 10 | 更多信息请参考 [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B) 项目。 11 | 12 | ## 更新 13 | 14 | ### **20230324** 15 | 1. 修复运行 chatglm_api.py 或 chatglm_api_macos 时可能发生文件中程序执行两次的问题； 16 | 2. 在 chatglm_api.py 中增加每次模型运行后清理显存的代码。 17 | 18 | 特别感谢 [@QNLanYang](https://github.com/QNLanYang/) 提出可以借鉴 [ChatGLM-webui](https://github.com/Akegarasu/ChatGLM-webui/blob/main/modules/model.py) 中清理显存的方案。 19 | 20 | ## 使用方式 21 | 22 | ### 环境安装 23 | 24 | 使用 pip 安装依赖：`pip install -r requirements.txt`，其中 `transformers` 库版本推荐为 `4.26.1`，但理论上不低于 `4.23.1` 即可。 25 | 26 | ### 代码调用 27 | 0. 下载本仓库 28 | ```shell 29 | git clone https://github.com/imClumsyPanda/ChatGLM-6B-API 30 | cd ChatGLM-6B-API 31 | ``` 32 | 1. 首先运行 chatglm_api 脚本 33 | - Windows 或 Linux 系统请运行 [chatglm_api.py](chatglm_api.py) 34 | - MacOS 系统请将完整模型下载至本地后，运行 [chatglm_api_macos.py](chatglm_api_macos.py)，脚本中模型存储路径为"./chatglm_hf_model/"，可依据实际情况进行修改。 35 | - 完整的模型实现可以在 [Hugging Face Hub](https://huggingface.co/THUDM/chatglm-6b) 上查看。如果你从Hugging Face Hub上下载checkpoint的速度较慢，也可以从[这里](https://cloud.tsinghua.edu.cn/d/fb9f16d6dc8f482596c2/)手动下载。 36 | 37 | 2. chatglm_api 脚本正常运行后，可以通过如下代码调用 ChatGLM-6B 模型来生成对话： 38 | 39 | ```python 40 | >>> import requests 41 | >>> user_msg, history = "你好", [] 42 | >>> resp = requests.post(f"http://127.0.0.1:8080/predict?user_msg={user_msg}", json=history) 43 | >>> if resp.status_code == 200: 44 | >>> response, history = resp.json()["response"], resp.json()["history"] 45 | >>> print(response) 46 | 你好👋!我是人工智能助手 ChatGLM-6B,很高兴见到你,欢迎问我任何问题。 47 | >>> user_msg = "晚上睡不着该怎么办" 48 | >>> resp = requests.post(f"http://127.0.0.1:8080/predict?user_msg={user_msg}", json=history) 49 | >>> if resp.status_code == 200: 50 | >>> response, history = resp.json()["response"], resp.json()["history"] 51 | >>> print(response) 52 | 晚上睡不着可能会让你感到焦虑或不舒服,但以下是一些可以帮助你入睡的方法: 53 | 54 | 1. 制定规律的睡眠时间表:保持规律的睡眠时间表可以帮助你建立健康的睡眠习惯,使你更容易入睡。尽量在每天的相同时间上床,并在同一时间起床。 55 | 2. 创造一个舒适的睡眠环境:确保睡眠环境舒适,安静,黑暗且温度适宜。可以使用舒适的床上用品,并保持房间通风。 56 | 3. 放松身心:在睡前做些放松的活动,例如泡个热水澡,听些轻柔的音乐,阅读一些有趣的书籍等,有助于缓解紧张和焦虑,使你更容易入睡。 57 | 4. 避免饮用含有咖啡因的饮料:咖啡因是一种刺激性物质,会影响你的睡眠质量。尽量避免在睡前饮用含有咖啡因的饮料,例如咖啡,茶和可乐。 58 | 5. 避免在床上做与睡眠无关的事情:在床上做些与睡眠无关的事情,例如看电影,玩游戏或工作等,可能会干扰你的睡眠。 59 | 6. 尝试呼吸技巧:深呼吸是一种放松技巧,可以帮助你缓解紧张和焦虑,使你更容易入睡。试着慢慢吸气,保持几秒钟,然后缓慢呼气。 60 | 61 | 如果这些方法无法帮助你入睡,你可以考虑咨询医生或睡眠专家,寻求进一步的建议。 62 | ``` 63 | 64 | ### Demo 65 | 66 | 本项目基于 [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B) 提供的 Demo，提供一个基于 [Gradio](https://gradio.app) 的网页版 Demo 和一个命令行 Demo。 67 | 68 | #### 网页版 Demo 69 | 70 | ![web-demo](resources/web-demo.png) 71 | 72 | 首先安装 Gradio：`pip install gradio`，然后运行仓库中的 [web_demo.py](web_demo.py)： 73 | 74 | ```shell 75 | python web_demo.py 76 | ``` 77 | 78 | 程序会运行一个 Web Server，并输出地址。在浏览器中打开输出的地址即可使用。 79 | 80 | #### 命令行 Demo 81 | 82 | ![cli-demo](resources/cli-demo.png) 83 | 84 | 运行仓库中 [cli_demo.py](cli_demo.py)： 85 | 86 | ```shell 87 | python cli_demo.py 88 | ``` 89 | 90 | 程序会在命令行中进行交互式的对话，在命令行中输入指示并回车即可生成回复，输入`clear`可以清空对话历史，输入`stop`终止程序。 91 | 92 | -------------------------------------------------------------------------------- /chatglm_api.py: -------------------------------------------------------------------------------- 1 | from fastapi import FastAPI 2 | from transformers import AutoModel, AutoTokenizer 3 | from typing import List 4 | import uvicorn 5 | import torch 6 | 7 | DEVICE = "cuda" 8 | DEVICE_ID = "0" 9 | CUDA_DEVICE = f"{DEVICE}:{DEVICE_ID}" if DEVICE_ID else DEVICE 10 | 11 | 12 | def torch_gc(): 13 | if torch.cuda.is_available(): 14 | with torch.cuda.device(CUDA_DEVICE): 15 | torch.cuda.empty_cache() 16 | torch.cuda.ipc_collect() 17 | 18 | 19 | app = FastAPI() 20 | tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", 21 | trust_remote_code=True 22 | ) 23 | model = AutoModel.from_pretrained("THUDM/chatglm-6b", 24 | trust_remote_code=True 25 | ).half().cuda() 26 | model = model.eval() 27 | 28 | 29 | @app.get("/") 30 | def hello(): 31 | return {"message": "Hello ChatGLM API!"} 32 | 33 | 34 | @app.post("/predict") 35 | def pred_chat(user_msg: str, 36 | history: List[List[str]], 37 | max_length: int = 2048, 38 | top_p: float = 0.7, 39 | temperature: float = 0.95, 40 | ): 41 | response, history = model.chat(tokenizer, 42 | user_msg, 43 | history, 44 | max_length=max_length, 45 | top_p=top_p, 46 | temperature=temperature 47 | ) 48 | #clear gpu cache 49 | torch_gc() 50 | return {"response": response, 51 | "history": history} 52 | 53 | 54 | if __name__ == "__main__": 55 | uvicorn.run(app=app, 56 | host="127.0.0.1", 57 | port=8080, 58 | reload=True) 59 | -------------------------------------------------------------------------------- /chatglm_api_macos.py: -------------------------------------------------------------------------------- 1 | from fastapi import FastAPI 2 | from transformers import AutoModel, AutoTokenizer 3 | from typing import List 4 | import uvicorn 5 | 6 | 7 | app = FastAPI() 8 | tokenizer = AutoTokenizer.from_pretrained("./chatglm_hf_model/", 9 | trust_remote_code=True 10 | ) 11 | model = AutoModel.from_pretrained("./chatglm_hf_model/", 12 | trust_remote_code=True 13 | ).float() 14 | model = model.eval() 15 | 16 | 17 | @app.get("/") 18 | def hello(): 19 | return {"message": "Hello ChatGLM API!"} 20 | 21 | 22 | @app.post("/predict") 23 | def pred_chat(user_msg: str, 24 | history: List[List[str]]): 25 | response, history = model.chat(tokenizer, user_msg, history) 26 | return {"response": response, 27 | "history": history} 28 | 29 | 30 | if __name__ == "__main__": 31 | uvicorn.run(app=app, 32 | host="127.0.0.1", 33 | port=8080, 34 | reload=True) -------------------------------------------------------------------------------- /cli_demo.py: -------------------------------------------------------------------------------- 1 | import platform 2 | import requests 3 | 4 | os_name = platform.system() 5 | 6 | history = [] 7 | print("欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序") 8 | while True: 9 | query = input("\n用户：") 10 | if query == "stop": 11 | break 12 | history = [] 13 | command = 'cls' if os_name == 'Windows' else 'clear' 14 | os.system(command) 15 | print("欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序") 16 | continue 17 | resp = requests.post(f"http://127.0.0.1:8080/predict?user_msg={query}", json=history) 18 | if resp.status_code == 200: 19 | response, history = resp.json()["response"], resp.json()["history"] 20 | else: 21 | response, history = "请求异常，请稍后再试", history 22 | print(f"ChatGLM-6B：{response}") 23 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | protobuf>=3.19.5,<3.20.1 2 | transformers>=4.26.1 3 | icetk 4 | cpm_kernels 5 | torch>=1.10 6 | fastapi 7 | uvicorn 8 | gradio -------------------------------------------------------------------------------- /resources/cli-demo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/imClumsyPanda/ChatGLM-6B-API/730779e94e6f2e7b6e32cbdbdb423ce1aa7022dd/resources/cli-demo.png -------------------------------------------------------------------------------- /resources/web-demo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/imClumsyPanda/ChatGLM-6B-API/730779e94e6f2e7b6e32cbdbdb423ce1aa7022dd/resources/web-demo.png -------------------------------------------------------------------------------- /web_demo.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import gradio as gr 3 | 4 | 5 | MAX_TURNS = 20 6 | MAX_BOXES = MAX_TURNS * 2 7 | 8 | 9 | def predict(input, history=None): 10 | if history is None: 11 | history = [] 12 | resp = requests.post(f"http://127.0.0.1:8080/predict?user_msg={input}", json=history) 13 | if resp.status_code == 200: 14 | response, history = resp.json()["response"], resp.json()["history"] 15 | else: 16 | response, history = "请求异常，请稍后再试", history 17 | updates = [] 18 | for query, response in history: 19 | updates.append(gr.update(visible=True, value="用户：" + query)) 20 | updates.append(gr.update(visible=True, value="ChatGLM-6B：" + response)) 21 | if len(updates) < MAX_BOXES: 22 | updates = updates + [gr.Textbox.update(visible=False)] * (MAX_BOXES - len(updates)) 23 | return [history] + updates 24 | 25 | 26 | with gr.Blocks() as demo: 27 | state = gr.State([]) 28 | text_boxes = [] 29 | for i in range(MAX_BOXES): 30 | if i % 2 == 0: 31 | text_boxes.append(gr.Markdown(visible=False, label="提问：")) 32 | else: 33 | text_boxes.append(gr.Markdown(visible=False, label="回复：")) 34 | 35 | with gr.Row(): 36 | with gr.Column(scale=4): 37 | txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter").style(container=False) 38 | with gr.Column(scale=1): 39 | button = gr.Button("Generate") 40 | button.click(predict, [txt, state], [state] + text_boxes) 41 | demo.queue().launch(share=False, 42 | server_name="0.0.0.0") 43 | --------------------------------------------------------------------------------