Update app.py

app.py

@@ -56,7 +56,7 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
         conversation.extend([{"role": "user", "content": prompt}, {"role": "assistant", "content": answer}])
     conversation.append({"role": "user", "content": message})
 
-    print(f"Conversation is -\n{conversation}")
+    #print(f"Conversation is -\n{conversation}")
     
     input_ids = tokenizer.apply_chat_template(conversation, tokenize=False, add_generation_prompt=True)
     inputs = tokenizer(input_ids, return_tensors="pt").to(0)
@@ -72,7 +72,7 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
         max_new_tokens=max_new_tokens, 
         do_sample=True, 
         temperature=temperature,
-        eos_token_id = [151645, 151643],
+        #eos_token_id = [151645, 151643],
     )
     
     thread = Thread(target=model.generate, kwargs=generate_kwargs)
@@ -109,7 +109,7 @@ with gr.Blocks(css=CSS) as demo:
                 minimum=128,
                 maximum=4096,
                 step=1,
-                value=1024,
+                value=256,
                 label="Max new tokens",
                 render=False,
             ),