abab112 commited on
Commit
f94c3a4
·
verified ·
1 Parent(s): e2b9836

Update OpenRSI repository link

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -31,7 +31,7 @@ tags:
31
  <p align="center">
32
  <a href="#paper-and-citation">📄 Paper</a>
33
  &nbsp;•&nbsp;
34
- <a href="https://github.com/rc314159-creator/OpenRSI">💻 Code</a>
35
  &nbsp;•&nbsp;
36
  <a href="https://rc314159-creator.github.io/OpenRSI/">🌐 Project</a>
37
  &nbsp;•&nbsp;
@@ -122,7 +122,7 @@ Frontis-MA1-35B uses full-parameter supervised fine-tuning followed by reinforce
122
  - GSPO with execution-grounded reward post-processing;
123
  - Adam optimizer with learning rate `1e-6`.
124
 
125
- See the paper and [OpenRSI code](https://github.com/rc314159-creator/OpenRSI) for the complete data-construction, training, search, and evaluation protocol.
126
 
127
  <p align="center">
128
  <img src="assets/paper-figure-openmle-framework.png" width="95%" alt="Paper framework figure: OpenMLE training and inference workflow">
 
31
  <p align="center">
32
  <a href="#paper-and-citation">📄 Paper</a>
33
  &nbsp;•&nbsp;
34
+ <a href="https://github.com/FrontisAI/OpenRSI">💻 Code</a>
35
  &nbsp;•&nbsp;
36
  <a href="https://rc314159-creator.github.io/OpenRSI/">🌐 Project</a>
37
  &nbsp;•&nbsp;
 
122
  - GSPO with execution-grounded reward post-processing;
123
  - Adam optimizer with learning rate `1e-6`.
124
 
125
+ See the paper and [OpenRSI code](https://github.com/FrontisAI/OpenRSI) for the complete data-construction, training, search, and evaluation protocol.
126
 
127
  <p align="center">
128
  <img src="assets/paper-figure-openmle-framework.png" width="95%" alt="Paper framework figure: OpenMLE training and inference workflow">