Update app.py

app.py

@@ -1,64 +1,28 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
+# 替换为你想使用的模型
+client = InferenceClient(model="Qwen/Qwen1.5-7B-Chat")
+
+def predict(message, history):
+    messages = [{"role": "system", "content": "You are a helpful assistant."}]
+    for human, bot in history:
+        messages.append({"role": "user", "content": human})
+        messages.append({"role": "assistant", "content": bot})
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+    partial_text = ""
+    for chunk in client.chat_completion(model="Qwen/Qwen1.5-7B-Chat",
+                                        messages=messages,
+                                        stream=True,
+                                        temperature=0.7,
+                                        top_p=0.95):
+        if chunk.choices and chunk.choices[0].delta and "content" in chunk.choices[0].delta:
+            partial_text += chunk.choices[0].delta["content"]
+            yield partial_text
+
+chat_interface = gr.ChatInterface(fn=predict, title="🌟 Streaming Chat with Qwen",
+                                  examples=["介绍一下你自己", "讲一个冷笑话", "什么是人工智能？"],
+                                  retry_btn=None, undo_btn="撤回", clear_btn="清空")
+
+chat_interface.queue().launch()