yungisimon/HAPPO-HATRPO
Reinforcement Learning • Updated
Simon Lee
yungisimon
AI & ML interests
None yet
Recent Activity
updated a model 3 days ago
yungisimon/HAPPO-HATRPO published a model 3 days ago
yungisimon/HAPPO-HATRPO updated a dataset 3 days ago
yungisimon/data_on_trialOrganizations
yungisimon/QWEN2.5-1.5B_1524524_msq_data_ablations_skip_step-msq_skip5-ep_3
2B • Updated • 2
yungisimon/QWEN2.5-1.5B_1524524_msq_data_ablations_skip_step-msq_skip5-ep_2
2B • Updated • 2
yungisimon/QWEN2.5-1.5B_1524524_msq_data_ablations_skip_step-msq_skip5-ep_1
2B • Updated • 1
yungisimon/QWEN2.5-1.5B_1524495_msq_data_ablations_skip_step-msq_skip4-ep_3
2B • Updated • 1
yungisimon/QWEN2.5-1.5B_1524495_msq_data_ablations_skip_step-msq_skip4-ep_2
2B • Updated • 1
yungisimon/QWEN2.5-1.5B_1524495_msq_data_ablations_skip_step-msq_skip4-ep_1
2B • Updated • 2
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-dare_linear-d0.7
15B • Updated • 2
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-dare_linear-d0.5
15B • Updated • 2
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-dare_linear-d0.3
15B • Updated • 1
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-dare_ties-d0.7
15B • Updated • 3
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-dare_ties-d0.5
15B • Updated • 4
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-dare_ties-d0.3
15B • Updated • 4
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-ties-d0.7
15B • Updated • 1
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-ties-d0.5
15B • Updated • 1
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-ties-d0.3
15B • Updated • 4
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-task
15B • Updated • 4
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-slerp-t0.7
15B • Updated • 1
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-slerp-t0.5
15B • Updated
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-slerp-t0.3
15B • Updated
yungisimon/QWEN2.5-14B-NQA-part1_part2-merge-linear
15B • Updated
yungisimon/QWEN2.5-14B_1520891_part2_b256-NQA_part1_b256-ep_3
15B • Updated
yungisimon/QWEN2.5-14B_1520891_part2_b256-NQA_part2_b256-ep_2
15B • Updated • 1
yungisimon/QWEN2.5-14B_1520891_part2_b256-NQA_part1_b256-ep_1
15B • Updated
yungisimon/QWEN2.5-14B_1520895_part1_b256-NQA_part1_b256-ep_3
15B • Updated
yungisimon/QWEN2.5-14B_1520895_part1_b256-NQA_part1_b256-ep_2
15B • Updated • 2
yungisimon/QWEN2.5-14B_1520895_part1_b256-NQA_part1_b256-ep_1
15B • Updated • 1
yungisimon/Qwen2.5-7B-100_1_2_3-merge-dare_linear-d0.7
8B • Updated
yungisimon/Qwen2.5-7B-100_1_2_3-merge-dare_linear-d0.5
8B • Updated • 5
yungisimon/Qwen2.5-7B-100_1_2_3-merge-dare_linear-d0.3
8B • Updated • 3