Update README.md

README.md

@@ -45,15 +45,22 @@ To run the inference on top of Llama 3.1 405B Instruct AWQ in INT4 precision, th
 
 ```python
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, AwqConfig
 
 model_id = "hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4"
+quantization_config = AwqConfig(
+    bits=4,
+    fuse_max_seq_len=512, # Note: Update this as per your use-case
+    do_fuse=True,
+)
+
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
   model_id,
   torch_dtype=torch.float16,
   low_cpu_mem_usage=True,
   device_map="auto",
+  quantization_config=quantization_config
 )
 
 prompt = [