Merge branch 'THUDM:main' into main

README.md

@@ -165,6 +165,13 @@ cd ChatGLM2-6B
 git clone https://huggingface.co/THUDM/chatglm2-6b
 ```
 
+如果你从 Hugging Face Hub 上下载 checkpoint 的速度较慢，可以只下载模型实现
+```Shell
+GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/THUDM/chatglm2-6b
+```
+然后从[这里](https://cloud.tsinghua.edu.cn/d/674208019e314311ab5c/)手动下载模型参数文件，并将下载的文件替换到本地的 `chatglm2-6b` 目录下。
+
+
 将模型下载到本地之后，将以上代码中的 `THUDM/chatglm2-6b` 替换为你本地的 `chatglm2-6b` 文件夹的路径，即可从本地加载模型。
 
 模型的实现仍然处在变动中。如果希望固定使用的模型实现以保证兼容性，可以在 `from_pretrained` 的调用中增加 `revision="v1.0"` 参数。`v1.0` 是当前最新的版本号，完整的版本列表参见 [Change Log](https://huggingface.co/THUDM/chatglm2-6b#change-log)。
@@ -225,6 +232,28 @@ curl -X POST "http://127.0.0.1:8000" \
   "time":"2023-03-23 21:38:40"
 }
 ```
+感谢 [@hiyouga]() 实现了 OpenAI 格式的流式 API 部署，可以作为任意基于 ChatGPT 的应用的后端，比如 [ChatGPT-Next-Web](https://github.com/Yidadaa/ChatGPT-Next-Web)。可以通过运行仓库中的[openai_api.py](openai_api.py) 进行部署：
+```shell
+python openai_api.py
+```
+进行 API 调用的示例代码为
+```python
+import openai
+if __name__ == "__main__":
+    openai.api_base = "http://localhost:8000/v1"
+    openai.api_key = "none"
+    for chunk in openai.ChatCompletion.create(
+        model="chatglm2-6b",
+        messages=[
+            {"role": "user", "content": "你好"}
+        ],
+        stream=True
+    ):
+        if hasattr(chunk.choices[0].delta, "content"):
+            print(chunk.choices[0].delta.content, end="", flush=True)
+```
+
+
 ## 低成本部署
 
 ### 模型量化

cli_demo.py

@@ -44,7 +44,8 @@ def main():
             os.system(clear_command)
             print("欢迎使用 ChatGLM2-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
             continue
-        count = 0
+        print("\nChatGLM：", end="")
+        current_length = 0
         for response, history, past_key_values in model.stream_chat(tokenizer, query, history=history,
                                                                     past_key_values=past_key_values,
                                                                     return_past_key_values=True):
@@ -52,13 +53,9 @@ def main():
                 stop_stream = False
                 break
             else:
-                count += 1
+                print(response[current_length:], end="", flush=True)
-                if count % 8 == 0:
+                current_length = len(response)
-                    os.system(clear_command)
+        print("")
-                    print(build_prompt(history), flush=True)
-                    signal.signal(signal.SIGINT, signal_handler)
-        os.system(clear_command)
-        print(build_prompt(history), flush=True)
 
 
 if __name__ == "__main__":

openai_api.py

@@ -0,0 +1,163 @@
+# coding=utf-8
+# Implements API for ChatGLM2-6B in OpenAI's format. (https://platform.openai.com/docs/api-reference/chat)
+# Usage: python openai_api.py
+# Visit http://localhost:8000/docs for documents.
+
+
+import time
+import torch
+import uvicorn
+from pydantic import BaseModel, Field
+from fastapi import FastAPI, HTTPException
+from contextlib import asynccontextmanager
+from starlette.responses import StreamingResponse
+from typing import Any, Dict, List, Literal, Optional, Union
+from transformers import AutoTokenizer, AutoModel
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI): # collects GPU memory
+    yield
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()
+        torch.cuda.ipc_collect()
+
+
+app = FastAPI(lifespan=lifespan)
+
+
+class ModelCard(BaseModel):
+    id: str
+    object: str = "model"
+    created: int = Field(default_factory=lambda: int(time.time()))
+    owned_by: str = "owner"
+    root: Optional[str] = None
+    parent: Optional[str] = None
+    permission: Optional[list] = None
+
+
+class ModelList(BaseModel):
+    object: str = "list"
+    data: List[ModelCard] = []
+
+
+class ChatMessage(BaseModel):
+    role: Literal["user", "assistant", "system"]
+    content: str
+
+
+class DeltaMessage(BaseModel):
+    role: Optional[Literal["user", "assistant", "system"]] = None
+    content: Optional[str] = None
+
+
+class ChatCompletionRequest(BaseModel):
+    model: str
+    messages: List[ChatMessage]
+    temperature: Optional[float] = None
+    top_p: Optional[float] = None
+    max_length: Optional[int] = None
+    stream: Optional[bool] = False
+
+
+class ChatCompletionResponseChoice(BaseModel):
+    index: int
+    message: ChatMessage
+    finish_reason: Literal["stop", "length"]
+
+
+class ChatCompletionResponseStreamChoice(BaseModel):
+    index: int
+    delta: DeltaMessage
+    finish_reason: Optional[Literal["stop", "length"]]
+
+
+class ChatCompletionResponse(BaseModel):
+    model: str
+    object: Literal["chat.completion", "chat.completion.chunk"]
+    choices: List[Union[ChatCompletionResponseChoice, ChatCompletionResponseStreamChoice]]
+    created: Optional[int] = Field(default_factory=lambda: int(time.time()))
+
+
+@app.get("/v1/models", response_model=ModelList)
+async def list_models():
+    global model_args
+    model_card = ModelCard(id="gpt-3.5-turbo")
+    return ModelList(data=[model_card])
+
+
+@app.post("/v1/chat/completions", response_model=ChatCompletionResponse)
+async def create_chat_completion(request: ChatCompletionRequest):
+    global model, tokenizer
+
+    if request.messages[-1].role != "user":
+        raise HTTPException(status_code=400, detail="Invalid request")
+    query = request.messages[-1].content
+
+    prev_messages = request.messages[:-1]
+    if len(prev_messages) > 0 and prev_messages[0].role == "system":
+        query = prev_messages.pop(0).content + query
+
+    history = []
+    if len(prev_messages) % 2 == 0:
+        for i in range(0, len(prev_messages), 2):
+            if prev_messages[i].role == "user" and prev_messages[i+1].role == "assistant":
+                history.append([prev_messages[i].content, prev_messages[i+1].content])
+
+    if request.stream:
+        generate = predict(query, history, request.model)
+        return StreamingResponse(generate, media_type="text/event-stream")
+
+    response, _ = model.chat(tokenizer, query, history=history)
+    choice_data = ChatCompletionResponseChoice(
+        index=0,
+        message=ChatMessage(role="assistant", content=response),
+        finish_reason="stop"
+    )
+
+    return ChatCompletionResponse(model=request.model, choices=[choice_data], object="chat.completion")
+
+
+async def predict(query: str, history: List[List[str]], model_id: str):
+    global model, tokenizer
+
+    choice_data = ChatCompletionResponseStreamChoice(
+        index=0,
+        delta=DeltaMessage(role="assistant"),
+        finish_reason=None
+    )
+    chunk = ChatCompletionResponse(model=model_id, choices=[choice_data], object="chat.completion.chunk")
+    yield "data: {}\n\n".format(chunk.json(exclude_unset=True, ensure_ascii=False))
+
+    current_length = 0
+
+    for new_response, _ in model.stream_chat(tokenizer, query, history):
+        if len(new_response) == current_length:
+            continue
+
+        new_text = new_response[current_length:]
+        current_length = len(new_response)
+
+        choice_data = ChatCompletionResponseStreamChoice(
+            index=0,
+            delta=DeltaMessage(content=new_text),
+            finish_reason=None
+        )
+        chunk = ChatCompletionResponse(model=model_id, choices=[choice_data], object="chat.completion.chunk")
+        yield "data: {}\n\n".format(chunk.json(exclude_unset=True, ensure_ascii=False))
+
+    choice_data = ChatCompletionResponseStreamChoice(
+        index=0,
+        delta=DeltaMessage(),
+        finish_reason="stop"
+    )
+    chunk = ChatCompletionResponse(model=model_id, choices=[choice_data], object="chat.completion.chunk")
+    yield "data: {}\n\n".format(chunk.json(exclude_unset=True, ensure_ascii=False))
+
+
+if __name__ == "__main__":
+    tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
+    model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).cuda()
+    model.eval()
+
+    uvicorn.run(app, host='0.0.0.0', port=8000, workers=1)