Update README.md

README.md

@@ -45,7 +45,7 @@ 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 = "psmathur/orca_mini_v2_13b"
 
@@ -62,7 +62,7 @@ q_config = {
     "q_group_size": 128,
 }
 
-load_quant = hf_hub_download('abhinavkulkarni/psmathur-orca_mini_v2_13b-w4-g128-awq', 'pytorch_model.bin')
+load_quant = snapshot_download('abhinavkulkarni/psmathur-orca_mini_v2_13b-w4-g128-awq')
 
 with init_empty_weights():
     model = AutoModelForCausalLM.from_pretrained(model_name, config=config,