Update README.md

README.md

@@ -9,19 +9,19 @@ language:
 ---
 
 
-# Xwen-72B-Chat
-
-<img src="Xwen-Cartoon.jpg" alt="Xwen-Cartoon" style="zoom:35%;" />
-
-## 1. Introduction
-
 > [!IMPORTANT]
 > If you enjoy our model, please **give it a like on our Hugging Face repo**. Your support means a lot to us. Thank you!
 
 > [!IMPORTANT]
-> You can download the **Q4_K_M GGUF files of Xwen-72B-Chat** at [this folder](https://huggingface.co/xwen-team/Xwen-72B-Chat/tree/main/Xwen-72B-Chat-GGUF).
+> You can download the **GGUF files of Xwen-72B-Chat** at [xwen-team/Xwen-72B-Chat-i1-GGUF](https://huggingface.co/xwen-team/Xwen-72B-Chat-i1-GGUF) (weighted/imatrix quants) and [xwen-team/Xwen-72B-Chat-GGUF](https://huggingface.co/xwen-team/Xwen-72B-Chat-GGUF) (static quants).
 
 
+# Xwen-72B-Chat
+
+<img src="Xwen-Cartoon.jpg" alt="Xwen-Cartoon" style="zoom:35%;" />
+
+## 1. Introduction
+
 Xwen is a series of open-sourced large language models (currently including **[Xwen-72B-Chat](https://huggingface.co/xwen-team/Xwen-72B-Chat)** and **[Xwen-7B-Chat](https://huggingface.co/xwen-team/Xwen-7B-Chat)**), post-trained from the pre-trained Qwen2.5 models (i.e., [Qwen2.5-72B](https://huggingface.co/Qwen/Qwen2.5-72B) and [Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B)) [1].
 
 **🏆 Top-1 chat performance!** To the best of our knowledge, at the time of Xwen models' release (February 1, 2025), **[Xwen-72B-Chat](https://huggingface.co/xwen-team/Xwen-72B-Chat) and [Xwen-7B-Chat](https://huggingface.co/xwen-team/Xwen-7B-Chat) exhibit the best chat performance among open-sourced models below 100B and 10B, respectively**, based on evaluation results from widely-used benchmarks such as Arena-Hard-Auto [2], MT-Bench [3], and AlignBench [4]. Please view details in the [Evaluation Results](https://huggingface.co/xwen-team/Xwen-72B-Chat#3-evaluation-results) part.