Update app.py

app.py

@@ -1,70 +1,122 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
+class VibeThinkerChat:
+    def __init__(self, model_path="WeiboAI/VibeThinker-1.5B"):
+        print("Loading model and tokenizer...")
+        self.model = AutoModelForCausalLM.from_pretrained(
+            model_path,
+            torch_dtype=torch.bfloat16,
+            trust_remote_code=True,
+            device_map="auto"
+        )
+        self.tokenizer = AutoTokenizer.from_pretrained(
+            model_path,
+            trust_remote_code=True
+        )
+        print("Model loaded successfully!")
+    
+    def generate_response(self, prompt, temperature=0.6, max_tokens=40960, top_p=0.95):
+        messages = [
+            {"role": "user", "content": prompt}
+        ]
+        
+        text = self.tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True
+        )
+        
+        model_inputs = self.tokenizer([text], return_tensors="pt").to(self.model.device)
+        
+        generation_config = dict(
+            max_new_tokens=max_tokens,
+            do_sample=True,
+            temperature=temperature,
+            top_p=top_p,
+            top_k=-1
+        )
+        
+        generated_ids = self.model.generate(
+            model_inputs.input_ids,
+            **generation_config
+        )
+        
+        generated_ids = [
+            output_ids[len(input_ids):] 
+            for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+        ]
+        
+        response = self.tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+        return response
 
-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="meta-llama/Llama-2-7b-chat-hf")
+# Initialize model
+chat_model = VibeThinkerChat()
 
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-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()
+def chat_interface(message, history, temperature, max_tokens):
+    try:
+        response = chat_model.generate_response(
+            message, 
+            temperature=temperature,
+            max_tokens=max_tokens
+        )
+        return response
+    except Exception as e:
+        return f"Error: {str(e)}"
 
+# Create Gradio interface
+with gr.Blocks(title="VibeThinker-1.5B Chat") as demo:
+    gr.Markdown("# 🧠 VibeThinker-1.5B Chat Interface")
+    gr.Markdown("A 1.5B parameter reasoning model optimized for math and coding problems.")
+    
+    with gr.Row():
+        with gr.Column(scale=3):
+            chatbot = gr.Chatbot(height=500)
+            msg = gr.Textbox(
+                label="Your Message",
+                placeholder="Ask a math or coding question...",
+                lines=3
+            )
+            with gr.Row():
+                submit = gr.Button("Submit", variant="primary")
+                clear = gr.Button("Clear")
+        
+        with gr.Column(scale=1):
+            temperature = gr.Slider(
+                minimum=0.1,
+                maximum=2.0,
+                value=0.6,
+                step=0.1,
+                label="Temperature",
+                info="Recommended: 0.6 or 1.0"
+            )
+            max_tokens = gr.Slider(
+                minimum=512,
+                maximum=40960,
+                value=4096,
+                step=512,
+                label="Max Tokens",
+                info="Maximum response length"
+            )
+    
+    def user_message(user_msg, history):
+        return "", history + [[user_msg, None]]
+    
+    def bot_response(history, temp, max_tok):
+        user_msg = history[-1][0]
+        bot_msg = chat_interface(user_msg, history, temp, max_tok)
+        history[-1][1] = bot_msg
+        return history
+    
+    msg.submit(user_message, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot_response, [chatbot, temperature, max_tokens], chatbot
+    )
+    submit.click(user_message, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot_response, [chatbot, temperature, max_tokens], chatbot
+    )
+    clear.click(lambda: None, None, chatbot, queue=False)
 
 if __name__ == "__main__":
+    demo.queue()
     demo.launch()