adding EXL2 reference (#15)

- adding EXL2 reference (ea64b7df052e112c24df3b067fc14ad90d4ed7eb)

README.md

@@ -125,7 +125,14 @@ This model is an advanced iteration of the powerful `Qwen/Qwen2.5-72B`, specific
 
 # ⚡ Quantized GGUF
 
-Here are the GGUF models thanks to [https://huggingface.co/bartowski](https://huggingface.co/bartowski): [calme-3.2-instruct-78b-GGUF](https://huggingface.co/bartowski/calme-3.2-instruct-78b-GGUF)
+Here are the GGUF models thanks to [bartowski](https://huggingface.co/bartowski): [calme-3.2-instruct-78b-GGUF](https://huggingface.co/bartowski/calme-3.2-instruct-78b-GGUF)
+
+# ⚡ Quantized EXL2
+
+Here is the EXL2 4.5 bits per weight (bpw) model thanks to [DavidCatalano](https://huggingface.co/DavidCatalano): [DavidCatalano/calme-3.2-instruct-78b-exl2](https://huggingface.co/DavidCatalano/calme-3.2-instruct-78b-exl2)
+
+DavidCatalano/calme-3.2-instruct-78b-exl2-4.5bpw.
+
 
 # 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
 Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__calme-3.2-instruct-78b)