Update app.py

app.py

@@ -3,7 +3,6 @@ import torch
 import bitsandbytes as bnb
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
-"""
 # BNB config
 bnb_config = BitsAndBytesConfig(
     load_in_4bit=True,
@@ -12,15 +11,14 @@ bnb_config = BitsAndBytesConfig(
     bnb_4bit_compute_dtype=torch.bfloat16
 )
 
-quantization_config=bnb_config
-"""
+#quantization_config=bnb_config
 
 # Define the BLOOM model name
 model_name = "CreitinGameplays/bloom-3b-conversational"
 
 # Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=bnb_config)
 
 def generate_text(user_prompt):
   """Generates text using the BLOOM model from Hugging Face Transformers and removes the user prompt."""