Added back quantization

app.py

@@ -3,17 +3,17 @@ import torch
 from transformers import AutoProcessor, LlavaForConditionalGeneration
 from transformers import BitsAndBytesConfig
 
-# quantization_config = BitsAndBytesConfig(
-#     load_in_4bit=True,
-#     bnb_4bit_compute_dtype=torch.float16
-# )
+quantization_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.float16
+)
 
 model_id = "llava-hf/llava-1.5-7b-hf"
 
 processor = AutoProcessor.from_pretrained(model_id)
 model = LlavaForConditionalGeneration.from_pretrained(
     model_id,
-    # quantization_config=quantization_config,
+    quantization_config=quantization_config,
     device_map="auto"
 )