Update README.md

README.md

@@ -1,3 +1,30 @@
----
-license: bsd-3-clause
----
+---
+library_name: transformers
+license: bsd-3-clause
+---
+
+# DeepSeek-R1-Distill-Qwen-1.5B-GPTQ-Int4
+
+This version of DeepSeek-R1-Distill-Qwen-1.5B has been converted to run on the Axera NPU using **w4a16** quantization.
+
+This model has been optimized with the following LoRA: 
+
+Compatible with Pulsar2 version: 3.4(Not released yet)
+
+## Useful links:
+[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) 
+
+## Support Platform
+
+- AX650
+  - AX650N DEMO Board
+  - M4N-Dock
+  - M.2 Accelerator card
+- AX630C
+  - *developing*
+ 
+|Chips|w8a16|w4a16|
+|--|--|--|
+|AX650| 11 tokens/sec|19 tokens/sec|