Update app.py

app.py

@@ -1,70 +1,69 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import pipeline
+import torch
+import spaces
 
+# Initialize the model pipeline
+model_id = "facebook/MobileLLM-R1-950M"
+pipe = pipeline(
+    "text-generation",
+    model=model_id,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
 
-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="facebook/MobileLLM-R1-950M")
-
-    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
-
+@spaces.GPU(duration=120)
+def respond(message, history):
+    prompt = ""
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            prompt += f"User: {user_msg}\n"
+        if assistant_msg:
+            prompt += f"Assistant: {assistant_msg}\n"
+    
+    # Add current message
+    prompt += f"User: {message}\nAssistant: "
+    
+    # Generate response with streaming
+    streamer = pipe.tokenizer.decode
+    
+    # Generate tokens
+    inputs = pipe.tokenizer(prompt, return_tensors="pt").to(pipe.model.device)
+    
+    with torch.no_grad():
+        outputs = pipe.model.generate(
+            **inputs,
+            max_new_tokens=10000,
+            temperature=0.7,
+            do_sample=True,
+            pad_token_id=pipe.tokenizer.eos_token_id,
+        )
+    
+    # Decode the generated tokens, skipping the input tokens
+    generated_tokens = outputs[0][inputs['input_ids'].shape[-1]:]
+    
+    # Stream the output token by token
+    response_text = ""
+    for i in range(len(generated_tokens)):
+        token = generated_tokens[i:i+1]
+        token_text = pipe.tokenizer.decode(token, skip_special_tokens=True)
+        response_text += token_text
+        yield response_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)",
-        ),
+# Create the chat interface
+demo = gr.ChatInterface(
+    fn=respond,
+    title="MobileLLM Chat",
+    description="Chat with Meta MobileLLM-R1-950M",
+    examples=[
+        "Write a Python function that returns the square of a number.",
+        "Compute: 1-2+3-4+5- ... +99-100.",
+        "Write a C++ program that prints 'Hello, World!'.",
+        "Explain how recursion works in programming.",
+        "What is the difference between a list and a tuple in Python?",
     ],
+    theme=gr.themes.Soft(),
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)