Update README.md

README.md

@@ -10,11 +10,22 @@ tags:
 - exaone
 ---
 
-<p align="center">
-<img src="https://cdn-uploads.huggingface.co/production/uploads/646410e04bf9122922289dc7/Ozoge_Be48YzVrKyElMbF.png", width="300", style="margin: 40 auto;">
-<br>
 
-# EXAONE-3.0-7.8B-Instruct
+<hr>
+
+# Llama.cpp imatrix quantizations of LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/646410e04bf9122922289dc7/Ozoge_Be48YzVrKyElMbF.png" alt="exaone" width="60%"/>
+
+Using llama.cpp commit [d565bb2](https://github.com/ggerganov/llama.cpp/commit/d565bb2fd5a2a58b9924a7a34e77a87c78c52137) for quantization.
+
+Original model: https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct
+
+All quants were made using the imatrix option and Bartowski's [calibration file](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8).
+
+<hr><br>
+
+# Original Model Card
 
 **👋👋 We have revised our [license](./LICENSE) for revitalizing the research ecosystem.👋👋**