Update README.md

README.md

@@ -11,7 +11,10 @@ This model has been optimized with the following LoRA:
 
 Compatible with Pulsar2 version: 3.4(Not released yet)
 
-## Useful links:
+## Convert tools links:
+
+For those who are interested in model conversion, you can try to export axmodel through the original repo : https://huggingface.co/jakiAJK/DeepSeek-R1-Distill-Qwen-1.5B_GPTQ-int4
+
 [Pulsar2 Link, How to Convert LLM from Huggingface to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/appendix/build_llm.html) 
 
 [AXera NPU LLM Runtime](https://github.com/AXERA-TECH/ax-llm) 
@@ -28,3 +31,10 @@ Compatible with Pulsar2 version: 3.4(Not released yet)
 |Chips|w8a16|w4a16|
 |--|--|--|
 |AX650| 11 tokens/sec|19 tokens/sec|
+
+## How to use
+
+### AX650 Host
+
+### AX650 M.2
+