Update README.md

README.md

@@ -11,6 +11,12 @@ tags:
 
 # Qwen2-72B-Instruct
 
+## Quantization
+
+This model is an exl2 quantisized model using [mixed-exl-calibration](https://huggingface.co/datasets/Orion-zhen/mixed-exl-calibration) as calibration dataset.
+
+Compared to normal wikitext calibration, this could provide slightly better performance on both English and Chinese, etc.
+
 ## Introduction
 
 Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 72B Qwen2 model.