Update app.py

app.py

@@ -17,7 +17,7 @@ print("Embedding model loaded...")
 
 # Loading the LLM
 callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
-'''
+
 llm = AutoModelForCausalLM.from_pretrained(
     "refuelai/Llama-3-Refueled",
     model_file="llama-2-7b-chat.Q3_K_S.gguf",
@@ -26,10 +26,7 @@ llm = AutoModelForCausalLM.from_pretrained(
     repetition_penalty=1.5,
     max_new_tokens=300,
 )
-'''
-model_id = "refuelai/Llama-3-Refueled"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-llm = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+
 
 print("LLM loaded...")