Update README.md

README.md

@@ -23,11 +23,22 @@ pip install torch transformers pillow
 import torch
 from PIL import Image
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import BitsAndBytesConfig
+
+
+bnb_cfg = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.float16,
+    llm_int8_skip_modules=["mm_projector", "vision_model"],
+)
 
 model_id = "qresearch/llama-3-vision-alpha-hf"
 model = AutoModelForCausalLM.from_pretrained(
-    model_id, trust_remote_code=True, torch_dtype=torch.float16
-).to("cuda")
+    model_name,
+    trust_remote_code=True,
+    torch_dtype=torch.float16,
+    quantization_config=bnb_cfg,
+)
 
 tokenizer = AutoTokenizer.from_pretrained(
     model_id,