resistz
/

TTCL-SimpleQA-RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K

Update README.md

0a1198b verified about 1 month ago

152 Bytes

license: mit

Test-time Calibration Learning (TTCL)

TTCL is performed on SimpleQA benchmark based on RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K.