wangzhengtao commited on
Commit
d03fdea
·
1 Parent(s): b9d0809

update README

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -29,6 +29,11 @@ pipeline_tag: image-text-to-text
29
  <b>📰&nbsp;&nbsp;<a href="https://www.kimi.com/blog/kimi-k2-5.html">Tech Blog</a></b>
30
  </p>
31
 
 
 
 
 
 
32
  ## 1. Model Introduction
33
 
34
  Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.
 
29
  <b>📰&nbsp;&nbsp;<a href="https://www.kimi.com/blog/kimi-k2-5.html">Tech Blog</a></b>
30
  </p>
31
 
32
+ 【Changelog】
33
+ - 2026.1.29:
34
+ - The default system prompt might cause confusion to users and unexpected behaviours, so we remove it.
35
+ - The token `<|media_start|>` is incorrect; it has been replaced with `<|media_begin|>` in the chat template.
36
+
37
  ## 1. Model Introduction
38
 
39
  Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.