Elliott commited on
Commit
944420c
·
verified ·
1 Parent(s): d85d173

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -1 +1,3 @@
1
- The base model used by LUFFY. We change to rope_theta from 10000 to 40000 and modify the chat_template for system prompt.
 
 
 
1
+ The base Qwen2.5-Math-7B model used by LUFFY.
2
+ We change to rope_theta from 10000 to 40000 and extend the context window to 16k.
3
+ Also, we modify the chat_template for the system prompt and add <think>.