parallel-reasoner/Qwen3-8B-sft-ours8x-rl-polaris-latency100-subtask100
8B • Updated • 15
checkpoints
-
-
parallel-reasoner/Qwen3-8B-sft-ours8x-rl-polaris-latency200
8B • Updated • 21 -
parallel-reasoner/Qwen3-8B-sft-ours8x-rl-polaris-latency100-subtask050
8B • Updated • 18 -
parallel-reasoner/Qwen3-8B-sft-ours8x-rl-polaris-latency100-subtask025
8B • Updated • 20 -
parallel-reasoner/Qwen3-8B-sft-ours8x-rl-polaris-latency100
8B • Updated • 22 -
parallel-reasoner/Qwen3-8B-sft-ours8x-rl-polaris-latency050
8B • Updated • 18 -
parallel-reasoner/real-trial-0.100-step-200-ant
8B • Updated • 6 -
parallel-reasoner/real-subtask-0.100-step-200-ant
8B • Updated • 51 -
parallel-reasoner/real-subtask-0.025-step-200-ant
8B • Updated • 6 -
parallel-reasoner/real-subtask-0.050-step-200-ant
8B • Updated • 5 -
parallel-reasoner/real-trial-0.05-200-ant
8B • Updated • 4 -
parallel-reasoner/real-trial-0.025-step-200-ant
8B • Updated • 4 -
parallel-reasoner/Qwen3-8B-sft-ours8x-rl-polaris-latency100-trial100
8B • Updated • 20 -
parallel-reasoner/Qwen3-8B-sft-ours8x-rl-polaris-latency100-trial025
8B • Updated • 20 -
parallel-reasoner/Qwen3-8B-sft-ours8x-rl-polaris-latency100-trial050
8B • Updated • 20