clean

app.py

@@ -12,20 +12,6 @@ model = AutoPeftModelForCausalLM.from_pretrained(
     )
 tokenizer = AutoTokenizer.from_pretrained("EITD/lora_model_1")
 
-# messages = [{"role": "user", "content": "Continue the Fibonacci sequence: 1, 1, 2, 3, 5, 8,"},]
-
-# inputs = tokenizer.apply_chat_template(
-#     messages,
-#     tokenize = True,
-#     add_generation_prompt = True, # Must add for generation
-#     return_tensors = "pt",
-# )
-
-# outputs = model.generate(input_ids = inputs, max_new_tokens = 64, use_cache = True,
-#                         temperature = 1.5, min_p = 0.1)
-
-# print(tokenizer.batch_decode(outputs))
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -72,7 +58,6 @@ def respond(
     # model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = max_tokens,
     #                 use_cache = True, temperature = temperature, min_p = top_p)
     response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
-    print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
 
     if "assistant" in response:
         response = response.split("assistant")[-1].strip()