Update app.py

app.py

@@ -6,7 +6,6 @@ import logging
 import sys
 import os
 from accelerate import infer_auto_device_map, init_empty_weights
-import bitsandbytes as bnb
 
 # Configure logging
 logging.basicConfig(
@@ -46,20 +45,14 @@ try:
     tokenizer.pad_token = tokenizer.eos_token
     logger.info("Tokenizer loaded successfully")
 
-    # Load model with quantization and device map
+    # Load model with basic configuration
     logger.info("Loading model...")
     model = AutoModelForCausalLM.from_pretrained(
         model_name,
         torch_dtype=torch.float16 if device == "cuda" else torch.float32,
         trust_remote_code=True,
         token=hf_token,
-        device_map="auto",
-        quantization_config={
-            "load_in_4bit": True,
-            "bnb_4bit_compute_dtype": torch.float16,
-            "bnb_4bit_use_double_quant": True,
-            "bnb_4bit_quant_type": "nf4"
-        }
+        device_map="auto"
     )
     logger.info("Model loaded successfully")