Small Fix Chat Interface

app.py

@@ -30,7 +30,9 @@ base_model = AutoModelForCausalLM.from_pretrained(
 
 # Load fine-tuned adapter
 model = PeftModel.from_pretrained(base_model, ADAPTER_ID, token=hf_token)
-tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, token=hf_token)
+
+# Load tokenizer from Instruct version (has chat template)
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B-Instruct", token=hf_token)
 tokenizer.pad_token = tokenizer.eos_token
 
 print("Model loaded successfully!")
@@ -76,6 +78,7 @@ demo = gr.ChatInterface(
         "Can you help me with a coding question?",
         "Tell me something interesting",
     ],
+    cache_examples=False,  # Disable caching to avoid startup issues
 )
 
 if __name__ == "__main__":