Update app.py

app.py

@@ -1,70 +1,55 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+import torch
 
+MODEL_ID = "caobin/llm-caobin"  
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
 
-    messages = [{"role": "system", "content": system_message}]
+def chat_fn(message, history):
+    input_text = ""
 
-    messages.extend(history)
+    
+    for user_msg, bot_msg in history:
+        input_text += f"<|user|>{user_msg}<|assistant|>{bot_msg}"
+    input_text += f"<|user|>{message}<|assistant|>"
 
-    messages.append({"role": "user", "content": message})
+    inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
 
-    response = ""
+    output_ids = model.generate(
+        **inputs,
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9,
+    )
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+    output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
 
-        response += token
-        yield response
+    # 只取 assistant 最新的回答
+    if "<|assistant|>" in output_text:
+        output_text = output_text.split("<|assistant|>")[-1]
 
+    return output_text
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+# Gradio UI
+with gr.Blocks(title="caobin LLM chatbot") as demo:
+    gr.Markdown("# 🤖 caobin 自定义 LLM 对话 Demo")
+
+    chatbot = gr.Chatbot(height=450)
+    msg = gr.Textbox(label="输入你的问题")
+
+    def respond(message, chat_history):
+        response = chat_fn(message, chat_history)
+        chat_history.append((message, response))
+        return "", chat_history
 
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()