Update README.md

README.md

@@ -9,10 +9,10 @@ license_link: LICENSE
 </h1>
 </div>
 
+[Switch to English](https://huggingface.co/IndexTeam/Index-1.9B-32K/blob/main/README.md) 
+
+[切换到中文](https://huggingface.co/IndexTeam/Index-1.9B-32K/blob/main/README_zh.md)
 
-<div style="text-align: center;">
-    [Switch to English](README.md) | [切换到中文](README_zh.md)
-</div>
 
 
 # Introduction
@@ -21,13 +21,13 @@ Index-1.9B-32K is a language model with only 1.9 billion parameters, yet it supp
 
 **Despite its small size (about 2% of models like GPT-4), Index-1.9B-32K demonstrates excellent long-text processing capabilities**. Below are comparison results with GPT-4 and GPT-3.5-turbo-16k:
 <div style="text-align: center;">
-    <img src="media/pk-all.png" alt="" width="800">
+    <img src="z-attach-pic-pk-all.png" alt="" width="800">
     <p><strong>Comparison of Index-1.9B-32K with GPT-4 and other models in long-text capability</strong></p>
 </div>
 
 In a 32K-length needle-in-a-haystack test, Index-1.9B-32K achieved excellent results, as shown in the figure below. The only exception was a small yellow spot (91.08 points) in the region of (32K length, 10% depth), with all other areas performing excellently in mostly green zones.
 <div style="text-align: center;">
-    <img src="media/needle-bench-en.png" alt="" width="900">
+    <img src="z-attach-pic-needle-bench-en.png" alt="" width="900">
     <p><strong>NeedleBench Evaluation</strong></p>
 </div>
 
@@ -64,7 +64,7 @@ CUDA_VISIBLE_DEVICES=0 python cli_long_text_demo.py --model_path '/path/to/model
 ```
 - Run & Interaction Example (Translation and summarization of the Bilibili financial report released on 2024.8.22 in English --- [Original English report here](https://github.com/bilibili/Index-1.9B/tree/main/demo/data/user_long_text.txt))：
 <div style="text-align: center;">
-    <img src="media/qa-mark.png" alt="" width="1000">
+    <img src="z-attach-pic-qa-mark.png" alt="" width="1000">
     <p><strong>Translation and Summary (Bilibili financial report released on 2024.8.22)</strong></p>
 </div>