Update app.py

app.py

@@ -13,9 +13,6 @@ def generate(prompt):
     yield prompt + "\n\nPrompt is too long. It needs to be less than 128 tokens."
   else:
     inputs = tokenizer(prompt, return_tensors="pt")
-    inputs["input_ids"][0][0] = 0
-    print(inputs)
-
     max_new_tokens = max(0, 128 - prompt_length)
     streamer = TextIteratorStreamer(tokenizer=tokenizer, skip_prompt=False, skip_special_tokens=True, timeout=300.0)
     thread = Thread(