Update app.py

app.py

@@ -58,25 +58,26 @@ def generate(req: UserInputRequest):
             {"role": "user", "content": req.user_input}
         ]
 
-        input_ids = tokenizer.apply_chat_template(
+        input_data = tokenizer.apply_chat_template(
             messages,
             add_generation_prompt=True,
-            return_tensors="pt"
+            return_tensors="pt",
+            padding=True
         ).to(model.device)
 
+        input_ids = input_data['input_ids']
+        attention_mask = input_data['attention_mask']
+
         terminators = [
             tokenizer.eos_token_id,
             tokenizer.convert_tokens_to_ids("<|eot_id|>")
         ]
 
         outputs = model.generate(
-            input_ids,
+            input_ids=input_ids,
+            attention_mask=attention_mask,
             max_new_tokens=200,
-            eos_token_id=terminators,
-            do_sample=False,
-            temperature=0.0,
-            top_p=1.0,
-            repetition_penalty=1.0
+            eos_token_id=terminators
         )
 
         response = outputs[0][input_ids.shape[-1]:]