Updated README

README.md

@@ -30,9 +30,9 @@ For Docker users, the `nvcr.io/nvidia/pytorch:23.06-py3` image is runtime v12.1
 ## How to Use
 
 ```bash
-git clone https://github.com/mit-han-lab/llm-awq \
+git clone https://github.com/abhinavkulkarni/llm-awq \
 && cd llm-awq \
-&& git checkout 71d8e68df78de6c0c817b029a568c064bf22132d \
+&& git checkout e977c5a570c5048b67a45b1eb823b81de02d0d60 \
 && pip install -e . \
 && cd awq/kernels \
 && python setup.py install
@@ -43,9 +43,9 @@ 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 = "mosaicml/mpt-7b-chat"
+model_name = "abhinavkulkarni/mosaicml-mpt-7b-chat-w4-g128-awq"
 
 # Config
 config = AutoConfig.from_pretrained(model_name, trust_remote_code=True)
@@ -60,7 +60,7 @@ q_config = {
     "q_group_size": 128,
 }
 
-load_quant = hf_hub_download('abhinavkulkarni/mosaicml-mpt-7b-chat-w4-g128-awq', 'pytorch_model.bin')
+load_quant = snapshot_download(model_name)
 
 with init_empty_weights():
     model = AutoModelForCausalLM.from_config(config=config,