Update README.md

README.md

@@ -40,7 +40,7 @@ import torch
 from awq.quantize.quantizer import real_quantize_model_weight
 from transformers import AutoModelForCausalLM, AutoConfig, AutoTokenizer
 from accelerate import init_empty_weights, load_checkpoint_and_dispatch
-from huggingface_hub import hf_hub_download
+from huggingface_hub import snapshot_download
 
 model_name = "tiiuae/falcon-40b-instruct"
 
@@ -57,7 +57,7 @@ q_config = {
     "q_group_size": 64,
 }
 
-load_quant = hf_hub_download('abhinavkulkarni/tiiuae-falcon-40b-instruct-w4-g128-awq', 'pytorch_model.bin')
+load_quant = snapshot_download('abhinavkulkarni/tiiuae-falcon-40b-instruct-w4-g128-awq', 'pytorch_model.bin')
 
 with init_empty_weights():
     model = AutoModelForCausalLM.from_config(config=config,