Update app.py

app.py

@@ -3,13 +3,10 @@ import torch
 from transformers import BitsAndBytesConfig, pipeline
 
 # Load model directly
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_compute_dtype=torch.float16
-)
+
 
 model_id = "liuhaotian/llava-v1.5-13b-shard3gb"
-pipe = pipeline("image-to-text", model=model_id, model_kwargs={"quantization_config": quantization_config})
+pipe = pipeline("image-to-text", model=model_id)
 
 def generate_text(image):
     max_new_tokens = 200