Update README.md

README.md

@@ -14,7 +14,6 @@ The following sample assumes that the setup on the above page has been completed
 
 This model has only been tested on RyzenAI for Windows 11. It does not work in Linux environments such as WSL.  
 
- 
 
 ### setup
 In cmd windows.
@@ -26,16 +25,12 @@ pip install transformers==4.43.3
 # Updating the Transformers library will cause the LLama 2 sample to stop working.  
 # If you want to run LLama 2, revert to pip install transformers==4.34.0.  
 pip install tokenizers==0.19.1
+pip install -U "huggingface_hub[cli]""
 
-git lfs install
-git clone https://huggingface.co/dahara1/llama3.1-8b-Instruct-amd-npu
-cd llama3.1-8b-Instruct-amd-npu
-git lfs pull
-cd ..
-copy <your_install_path>\RyzenAI-SW\example\transformers\models\llama2\modeling_llama_amd.py .
+huggingface-cli download dahara1/llama3.1-8b-Instruct-amd-npu --revision main --local-dir llama3.1-8b-Instruct-amd-npu
 
 # set up Runtime. see https://ryzenai.docs.amd.com/en/latest/runtime_setup.html
-set XLNX_VART_FIRMWARE=<your_install_path>\voe-4.0-win_amd64\1x4.xclbin
+set XLNX_VART_FIRMWARE=<your_firmware_install_path>\voe-4.0-win_amd64\1x4.xclbin
 set NUM_OF_DPU_RUNNERS=1
 
 # save below sample script as utf8 and llama-3.1-test.py
@@ -83,7 +78,7 @@ if __name__ == "__main__":
     torch.set_num_threads(4)
 
     tokenizer = AutoTokenizer.from_pretrained("llama3.1-8b-Instruct-amd-npu")
-    ckpt = "llama3.1-8b-Instruct-amd-npu/llama3.1_8b_w_bit_4_awq_amd.pt"
+    ckpt = r"llama3.1-8b-Instruct-amd-npu\llama3.1_8b_w_bit_4_awq_amd.pt"
     terminators = [
         tokenizer.eos_token_id,
         tokenizer.convert_tokens_to_ids("<|eot_id|>")