Update README.md

Added EXL2 quants thanks to LoneStriker and GGUF quants thanks to NanoByte!

README.md

@@ -18,7 +18,8 @@ license: other
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6303ca537373aacccd85d8a7/RFEW_K0ABp3k_N3j02Ki4.jpeg)
 
-- GGUF: [wolfram/miquliz-120b-GGUF](https://huggingface.co/wolfram/miquliz-120b-GGUF)
+- EXL2: [2.4bpw](https://huggingface.co/LoneStriker/miquliz-120b-2.4bpw-h6-exl2) | [2.65bpw](https://huggingface.co/LoneStriker/miquliz-120b-2.65bpw-h6-exl2) | [2.9bpw](https://huggingface.co/LoneStriker/miquliz-120b-2.9bpw-h6-exl2) | [4.0bpw](https://huggingface.co/LoneStriker/miquliz-120b-4.0bpw-h6-exl2) |
+- GGUF: [IQ3_XXS](https://huggingface.co/wolfram/miquliz-120b-GGUF) | [Q4_K_S+Q4_K_M](https://huggingface.co/NanoByte/miquliz-120b-Q4-GGUF)
 
 This is a 120b frankenmerge created by interleaving layers of [miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf) with [lzlv_70b_fp16_hf](https://huggingface.co/lizpreciatior/lzlv_70b_fp16_hf) using [mergekit](https://github.com/cg123/mergekit).
 
@@ -26,6 +27,8 @@ Inspired by [goliath-120b](https://huggingface.co/alpindale/goliath-120b).
 
 Thanks for the support, [CopilotKit](https://github.com/CopilotKit/CopilotKit) - the open-source platform for building in-app AI Copilots into any product, with any LLM model. Check out their GitHub.
 
+Thanks for the EXL2 and GGUF quants, [Lone Striker](https://huggingface.co/LoneStriker) and [NanoByte](https://huggingface.co/NanoByte)!
+
 ## Prompt template: Mistral
 
 ```