Update app.py

app.py

@@ -3,6 +3,7 @@ import torch
 import bitsandbytes as bnb
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
+"""
 # BNB config
 bnb_config = BitsAndBytesConfig(
     load_in_4bit=True,
@@ -10,6 +11,7 @@ bnb_config = BitsAndBytesConfig(
     bnb_4bit_quant_type="nf4",
     bnb_4bit_compute_dtype=torch.bfloat16
 )
+"""
 
 #quantization_config=bnb_config
 
@@ -18,7 +20,7 @@ model_name = "CreitinGameplays/bloom-3b-conversational"
 
 # Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=bnb_config)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 def generate_text(user_prompt):
   """Generates text using the BLOOM model from Hugging Face Transformers and removes the user prompt."""