Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,62 @@
+import gradio as gr
+from transformers import pipeline
+import torch
+
+# Initialize the model pipeline
+model_id = "facebook/MobileLLM-R1-950M"
+pipe = pipeline(
+    "text-generation",
+    model=model_id,
+    torch_dtype="auto",
+    device_map="auto",
+)
+
+def respond(message, history):
+    # Convert history to messages format
+    messages = []
+    
+    # Add conversation history
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
+    
+    # Add current message
+    messages.append({"role": "user", "content": message})
+    
+    # Generate response
+    outputs = pipe(
+        messages,
+        max_new_tokens=512,
+        temperature=0.7,
+        do_sample=True,
+        pad_token_id=pipe.tokenizer.eos_token_id,
+    )
+    
+    # Extract only the assistant's response
+    generated_text = outputs[0]["generated_text"]
+    assistant_response = generated_text[-1]["content"]
+    
+    return assistant_response
+
+# Create the chat interface
+demo = gr.ChatInterface(
+    fn=respond,
+    title="MobileLLM Chat",
+    description="Chat with Facebook's MobileLLM-R1-950M model",
+    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?",
+    ],
+    retry_btn=None,
+    undo_btn=None,
+    clear_btn="Clear",
+    theme=gr.themes.Soft(),
+)
+
+if __name__ == "__main__":
+    demo.launch()