resistz
/

TTCL-SimpleQA-RLCR-Qwen3-4B-DAPO-Math14K

Model card Files Files and versions

resistz commited on Sep 28

Commit

d08e809

·

verified ·

1 Parent(s): e28c088

Update README.md

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -1,3 +1,6 @@
 ---
 license: mit
 ---

 ---
 license: mit
 ---
+**Test-time Calibration Learning (TTCL)**
+TTCL is performed on **SimpleQA** benchmark based on RLCR-calibrated Qwen3-4B on DAPO-Math-14K.