Update app.py

app.py

@@ -39,11 +39,13 @@ def create_llm():
     """Initialize the language model with optimized parameters"""
     
     
-    bnb_config = BitsAndBytesConfig(
-        load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16
-    )
+    # bnb_config = BitsAndBytesConfig(
+    #     load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16
+    # )
     
-    model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, quantization_config=bnb_config)
+    model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, 
+                                                 # quantization_config=bnb_config
+                                                )
     tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
     
     terminators = [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>")]