Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 import logging
 import sys
@@ -61,15 +61,15 @@ try:
     )
 
     with timer("Loading model"):
-        model = AutoModelForCausalLM.from_pretrained(
-            model_id,
-            quantization_config=bnb_config,
-            device_map={"": "cpu"},  # Explicitly set to CPU
-            trust_remote_code=True,
-            force_download=True,
-            cache_dir='./cache'
-        )
+    model = AutoModelForCausalLM.from_pretrained(
+        model_id,
+        device_map={"": "cpu"},
+        trust_remote_code=True,
+        force_download=True,
+        cache_dir='./cache'
+    )
         model.eval()
+
     logger.info("Model loaded successfully")
 
     def generate_text(prompt, max_tokens=100, temperature=0.7):