Update README.md

README.md

@@ -1,4 +1,9 @@
 run phi3-mini on AMD NPU
 
+1. Use awq quantization for the original model(get ```phi3_mini_awq_4bit_no_flash_attention.pt```).
+2. run ```python run_awq.py --task decode --target aie --w_bit 4```
 
-reference:https://github.com/amd/RyzenAI-SW/tree/main/example/transformers
+
+reference:https://github.com/amd/RyzenAI-SW/tree/main/example/transformers
+
+As the quantization of phi-3, may refer to https://github.com/mit-han-lab/llm-awq/pull/183