Update app.py

app.py

@@ -1,6 +1,6 @@
 import os
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline,BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import gradio as gr
 
 
@@ -10,25 +10,14 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 os.environ['HF_TOKEN']=os.environ.get('HF_TOKEN')
 os.environ['HUGGINGFACEHUB_API_TOKEN']=os.environ.get('HF_TOKEN')
 
-# Configure quantization for CPU
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_compute_dtype=torch.bfloat16,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4"
-)
 
 # Load the model with quantization
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     torch_dtype=torch.bfloat16,
-    device_map="auto",
-    quantization_config=quantization_config
+    device_map="auto"
 )
 
-# Set the device to CPU
-device = "cpu"
-# model.to(device)
 
 # Define the function for the Gradio interface
 def chat_with_phi(message):