SISReL
/

math-RLRTcorrect-RLSDincorrect-Qwen3-4B-Base-1.0

Model card Files Files and versions

math-RLRTcorrect-RLSDincorrect-Qwen3-4B-Base-1.0 / global_step_20

Commit History

Jun 1

16:54
remove global_step_20/actor

SISReL

Verified signature
dc09819
15:00
add global_step_20/actor

SISReL

Verified signature
0374498
14:58
add global_step_20/output_hf_model

SISReL

Verified signature
f5e5bd3