Update app.py

app.py

@@ -1,64 +1,59 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+import torch, gradio as gr
 
-"""
-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")
+model_id = "sunhaonlp/Qwen2.5_7B_Instruct_ZeroSearch_wiki_V2"
 
-
-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]})
-
-    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)",
-        ),
-    ],
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.float32
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    quantization_config=bnb_config,
+    device_map="auto",
+    trust_remote_code=True
+)
+model.eval()
+
+def build_prompt(history, query):
+    messages = [{"role": "system", "content": "你是一个聪明幽默、知识全面的中文AI助手。"}]
+    for user, bot in history:
+        messages.append({"role": "user", "content": user})
+        messages.append({"role": "assistant", "content": bot})
+    messages.append({"role": "user", "content": query})
+    return tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+def chat(query, history=[]):
+    prompt = build_prompt(history, query)
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    output = model.generate(
+        **inputs,
+        max_new_tokens=512,
+        temperature=0.7,
+        top_p=0.9,
+        repetition_penalty=1.1,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    result = tokenizer.decode(output[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
+    history.append((query, result.strip()))
+    return result.strip(), history
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 🧠 Qwen2.5 中文助手（CPU 免费版）")
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(placeholder="来问我点什么吧，比如：美股怎么开户？")
+    state = gr.State([])
+    send = gr.Button("发送")
+
+    def user_input(user_msg, history):
+        reply, history = chat(user_msg, history)
+        return history + [(user_msg, reply)], history
+
+    send.click(user_input, [msg, state], [chatbot, state])
+    msg.submit(user_input, [msg, state], [chatbot, state])
+
+demo.launch()