uavleeva/grpo_mixed_run_004
Updated
Multitask RLVR using GRPO (HSE Project)
-
-
uavleeva/grpo_mixed_run_001
Updated -
uavleeva/grpo_math_run_level3_all_rewards_001
Updated -
uavleeva/grpo_sql_run_004
Updated -
uavleeva/grpo_code_run_001
Updated -
uavleeva/grpo_sql_run_005
Updated -
uavleeva/grpo_sql_run_002
Updated -
uavleeva/grpo_mixed_run_002
Updated -
uavleeva/grpo_code_run_002
Updated -
uavleeva/grpo_merged_math_sql_code_ties_001
Text Generation • Updated • 1 -
uavleeva/grpo_merged_math_sql_code_linear_001
Text Generation • Updated -
uavleeva/grpo_math_run_level3_accformat_001
Updated -
open-r1/Big-Math-RL-Verified-Processed
Viewer • Updated • 1M • 584 • 26 -
uavleeva/text2sql_synthetics
Viewer • Updated • 100 • 8 -
open-r1/verifiable-coding-problems-python
Viewer • Updated • 35.7k • 379 • 12