Update README.md

Add links to EXL2 quants

README.md

@@ -12,6 +12,8 @@ language:
 # WestLake-10.7B-v2: Role-Play & Text Generation Specialist Model
 
 [GGUF version available here](https://huggingface.co/froggeric/WestLake-10.7B-v2-GGUF)
+**EXL2 versions available here:**
+[3.3bpw](https://huggingface.co/StopTryharding/WestLake-10.7B-v2-exl2-3.3) / [4.0bpw](https://huggingface.co/StopTryharding/WestLake-10.7B-v2-exl2-4.0) / [5.0bpw](https://huggingface.co/StopTryharding/WestLake-10.7B-v2-exl2-5.0) / [6.0bpw](https://huggingface.co/StopTryharding/WestLake-10.7B-v2-exl2-6.0) / [8.0bpw](https://huggingface.co/StopTryharding/WestLake-10.7B-v2-exl2-8.0)
 
 This is my first viable self-merge of the fantastic WestLake-7B-v2 model, obtained after more than 12 rounds of testing different
 merge configurations. In my [LLM Creativity Benchmark](https://huggingface.co/datasets/froggeric/creativity), it greatly improves over the original 7B model, and ranks between miqu-1-120b