Upload 4 files

app.py

@@ -0,0 +1,100 @@
+import os
+os.system('pip install dashscope')
+import gradio as gr
+from http import HTTPStatus
+import dashscope
+from dashscope import Generation
+from dashscope.api_entities.dashscope_response import Role
+from typing import List, Optional, Tuple, Dict
+from urllib.error import HTTPError
+default_system = 'You are a helpful assistant.'
+
+
+YOUR_API_TOKEN = os.getenv('YOUR_API_TOKEN')
+dashscope.api_key = YOUR_API_TOKEN
+
+History = List[Tuple[str, str]]
+Messages = List[Dict[str, str]]
+
+def clear_session() -> History:
+    return '', []
+
+def modify_system_session(system: str) -> str:
+    if system is None or len(system) == 0:
+        system = default_system
+    return system, system, []
+
+def history_to_messages(history: History, system: str) -> Messages:
+    messages = [{'role': Role.SYSTEM, 'content': system}]
+    for h in history:
+        messages.append({'role': Role.USER, 'content': h[0]})
+        messages.append({'role': Role.ASSISTANT, 'content': h[1]})
+    return messages
+
+
+def messages_to_history(messages: Messages) -> Tuple[str, History]:
+    assert messages[0]['role'] == Role.SYSTEM
+    system = messages[0]['content']
+    history = []
+    for q, r in zip(messages[1::2], messages[2::2]):
+        history.append([q['content'], r['content']])
+    return system, history
+
+
+def model_chat(query: Optional[str], history: Optional[History], system: str
+) -> Tuple[str, str, History]:
+    if query is None:
+        query = ''
+    if history is None:
+        history = []
+    messages = history_to_messages(history, system)
+    messages.append({'role': Role.USER, 'content': query})
+    gen = Generation.call(
+        model = "qwen1.5-32b-chat",
+        messages=messages,
+        result_format='message',
+        stream=True
+    )
+    for response in gen:
+        if response.status_code == HTTPStatus.OK:
+            role = response.output.choices[0].message.role
+            response = response.output.choices[0].message.content
+            system, history = messages_to_history(messages + [{'role': role, 'content': response}])
+            yield '', history, system
+        else:
+            raise HTTPError('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
+                response.request_id, response.status_code,
+                response.code, response.message
+            ))
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("""<p align="center"><img src="https://modelscope.oss-cn-beijing.aliyuncs.com/resource/qwen.png" style="height: 80px"/><p>""")  ## todo
+    gr.Markdown("""<center><font size=8>Qwen-32B-Chat Bot👾</center>""")
+    gr.Markdown("""<center><font size=4>通义千问-32B（Qwen-32B） 是阿里云研发的通义千问大模型系列的720亿参数规模的模型。</center>""")
+
+    with gr.Row():
+        with gr.Column(scale=3):
+            system_input = gr.Textbox(value=default_system, lines=1, label='System')
+        with gr.Column(scale=1):
+            modify_system = gr.Button("🛠️ 设置system并清除历史对话", scale=2)
+        system_state = gr.Textbox(value=default_system, visible=False)
+    chatbot = gr.Chatbot(label='Qwen-32B-Chat')
+    textbox = gr.Textbox(lines=2, label='Input')
+
+    with gr.Row():
+        clear_history = gr.Button("🧹 清除历史对话")
+        sumbit = gr.Button("🚀 发送")
+
+    sumbit.click(model_chat,
+                 inputs=[textbox, chatbot, system_state],
+                 outputs=[textbox, chatbot, system_input])
+    clear_history.click(fn=clear_session,
+                        inputs=[],
+                        outputs=[textbox, chatbot])
+    modify_system.click(fn=modify_system_session,
+                        inputs=[system_input],
+                        outputs=[system_state, system_input, chatbot])
+
+demo.queue(api_open=False)
+demo.launch(max_threads=30)

cli_demo.py

@@ -0,0 +1,58 @@
+import os
+import platform
+import signal
+from transformers import AutoTokenizer, AutoModel
+import readline
+
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+model = model.eval()
+
+os_name = platform.system()
+clear_command = 'cls' if os_name == 'Windows' else 'clear'
+stop_stream = False
+
+
+def build_prompt(history):
+    prompt = "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"
+    for query, response in history:
+        prompt += f"\n\n用户：{query}"
+        prompt += f"\n\nChatGLM-6B：{response}"
+    return prompt
+
+
+def signal_handler(signal, frame):
+    global stop_stream
+    stop_stream = True
+
+
+def main():
+    history = []
+    global stop_stream
+    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")
+    while True:
+        query = input("\n用户：")
+        if query.strip() == "stop":
+            break
+        if query.strip() == "clear":
+            history = []
+            os.system(clear_command)
+            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")
+            continue
+        count = 0
+        for response, history in model.stream_chat(tokenizer, query, history=history):
+            if stop_stream:
+                stop_stream = False
+                break
+            else:
+                count += 1
+                if count % 8 == 0:
+                    os.system(clear_command)
+                    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__":
+    main()

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,2 @@
+gradio==4.29.0
+gradio_client