Update app.py


app.py

@@ -13,23 +13,14 @@ import re
 import numpy as np
 import datetime
 import subprocess
-
 # Ensure nltk punkt is downloaded
 nltk.download('punkt')
 
-# Configuration for quantization
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_compute_dtype=torch.float16
-)
-
 # Model ID
 model_id = "llava-hf/llava-1.5-7b-hf"
 
-# Load the pipeline
-pipe = pipeline("image-to-text",
-                model=model_id,
-                model_kwargs={"quantization_config": quantization_config})
+# Load the pipeline without GPU-dependent quantization
+pipe = pipeline("image-to-text", model=model_id)
 
 # Initialize Whisper model
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"