Trained ExpRL checkpoints. Paper link: https://arxiv.org/abs/2606.17024
Violet Xiang PRO
violetxi
AI & ML interests
None yet
Recent Activity
published a model 2 days ago
U-WIN/qwen35-9b-equational-theory-mix1m-grpo200-ntp-strategy-32k updated a model 2 days ago
U-WIN/qwen35-9b-equational-theory-mix1m-grpo200-ntp-strategy-32k published a model 2 days ago
U-WIN/qwen35-9b-equational-theory-mix1m-grpo200-ntp-summary-32kOrganizations
models 97
violetxi/hparam-92m-block-mtp-truncated-peak_lr-1e-3-wu-0p01-s42
Text Generation • 92.1M • Updated • 438 • 1
violetxi/hparam-92m-block-mtp-truncated-peak_lr-3e-5-wu-0p05-s42
Text Generation • 92.1M • Updated • 392
violetxi/hparam-92m-block-mtp-truncated-peak_lr-3e-5-wu-0p01-s42
Text Generation • 92.1M • Updated • 330
violetxi/hparam-92m-block-mtp-truncated-peak_lr-1e-5-wu-0p05-s42
Text Generation • 92.1M • Updated • 166
violetxi/hparam-92m-block-mtp-truncated-peak_lr-1e-5-wu-0p01-s42
Text Generation • 92.1M • Updated • 164
violetxi/hparam-92m-block-mtp-truncated-peak_lr-1e-4-wu-0p01-s42
Text Generation • 92.1M • Updated • 161 • 1
violetxi/hparam-92m-block-mtp-truncated-peak_lr-1e-4-wu-0p05-s42
Text Generation • 92.1M • Updated • 80
violetxi/hparam-92m-block-mtp-truncated-peak_lr-3e-3-wu-0p05-s42
Text Generation • 92.1M • Updated • 75
violetxi/hparam-92m-block-mtp-truncated-peak_lr-3e-4-wu-0p05-s42
Text Generation • 92.1M • Updated • 75
violetxi/hparam-92m-block-mtp-truncated-peak_lr-1e-3-wu-0p05-s42
Text Generation • 92.1M • Updated • 83
datasets 206
violetxi/chess-20m-tactical-eval-traces
Viewer • Updated • 31.1k • 36
violetxi/chess_puzzle_training_datasets_lt-2400
Viewer • Updated • 221k • 78
violetxi/qwen35-4b-tmax-16turn-unfinished-trajectories
Viewer • Updated • 77 • 57
violetxi/tmax-qwen35-4b-hosted-16x8-b200
Viewer • Updated • 128 • 33
violetxi/toolathlon-qwen35-4b-base-pass1-pilot15
Viewer • Updated • 15 • 44
violetxi/tb21-eval-qwen35-action-only-20k-infra-repaired-c164-max32k-timeout2x
Viewer • Updated • 445 • 32
violetxi/tb21-eval-qwen35-action-only-40k-c164-max32k-timeout8x
Viewer • Updated • 445 • 26
violetxi/tb21-eval-qwen35-original-w005-20k-thinking-32k-timeout8x
Viewer • Updated • 445 • 31
violetxi/tb21-eval-qwen35-4b-offline-echo-action-only-10k-tacc-timeout2x
Viewer • Updated • 445 • 38
violetxi/tb21-eval-qwen35-4b-base-thinking-full
Viewer • Updated • 445 • 46