Update app.py

app.py

@@ -118,7 +118,7 @@ def respond(
 
     messages.append({"role": "user", "content": message})
     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(accelerator.device) #.to('cuda')
-    print(input_ids)
+    input_str= str(input_ids)
 ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
     # with autocast():
     gen_tokens = model.generate(
@@ -130,6 +130,7 @@ def respond(
 
     gen_text = tokenizer.decode(gen_tokens[0])
     print(gen_text)
+    gen_text= gen_text.replace(input_str,'')
     
     yield gen_text