Create app.py

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the model and tokenizer
+checkpoint = "HuggingFaceTB/SmolLM2-135M-Instruct"
+device = "cpu" # Since we are on free tier CPU
+
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
+
+def chat(message, history):
+    # Prepare the chat history for the model
+    # SmolLM2 uses a specific 'instruct' format
+    messages = [{"role": "system", "content": "You are a helpful assistant."}]
+    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})
+    
+    # Convert to model-ready format
+    input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    inputs = tokenizer(input_text, return_tensors="pt").to(device)
+    
+    # Generate response
+    outputs = model.generate(**inputs, max_new_tokens=500, temperature=0.7, top_p=0.9, do_sample=True)
+    response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
+    
+    return response
+
+# Create the Gradio interface
+demo = gr.ChatInterface(fn=chat, title="SmolLM2-135M Personal Assistant")
+
+if __name__ == "__main__":
+    demo.launch()
+