Update app.py

app.py

@@ -12,7 +12,7 @@ def predict(message, history):
     history.append({"role": "user", "content": message})
     input_text = tokenizer.apply_chat_template(history, tokenize=False) + "<|start_header_id|>assistant<|end_header_id|>\n\n"
     inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)  
-    outputs = model.generate(inputs, max_new_tokens=100, temperature=0.7, top_p=0.9, do_sample=True)
+    outputs = model.generate(inputs, max_new_tokens=1024, temperature=0.7, top_p=0.9, do_sample=True)
     decoded = tokenizer.decode(outputs[0])
     response = decoded.split("<|start_header_id|>assistant<|end_header_id|>\n\n")[-1]
     return response