Trained ExpRL checkpoints. Paper link: https://arxiv.org/abs/2606.17024
Violet Xiang PRO
violetxi
AI & ML interests
None yet
Recent Activity
updated a model 38 minutes ago
violetxi/chess-5epochs-block-mtp-full-bptt-20m updated a model 38 minutes ago
violetxi/chess-5epochs-block-mtp-truncated-bptt-20m published a model about 1 hour ago
violetxi/chess-5epochs-block-mtp-full-bptt-20mOrganizations
models 78
violetxi/chess-5epochs-block-mtp-full-bptt-20m
Updated
violetxi/chess-5epochs-block-mtp-truncated-bptt-20m
Updated
violetxi/chess-looped-20m-block-mtp-full-bptt-4xh100
Updated
violetxi/chess-looped-20m-block-mtp-truncated-bptt-4xh100
Updated
violetxi/chess-looped-20m-unmask-teacher-full-bptt-mb64
Updated
violetxi/chess-looped-20m-unmask-self-full-bptt-mb64
Updated
violetxi/qwen3-8b-advice-stargate-v1
8B • Updated • 13
violetxi/qwen3-8b-advice-A0v2-hybrid-a40b60
8B • Updated • 2
violetxi/qwen3-8b-advice-A0-elicitation-kl001-v3
8B • Updated • 4
violetxi/qwen3-8b-advice-A0v2-hybrid-a30b70
8B • Updated • 3
datasets 208
violetxi/ch-pilot-rollouts-qwen3.5-9b
Viewer • Updated • 296 • 27
violetxi/ch-pilot-rollouts-qwen3.5-35b-a3b
Viewer • Updated • 261 • 30
violetxi/chess-20m-tactical-eval-traces
Viewer • Updated • 31.1k • 67
violetxi/chess_puzzle_training_datasets_lt-2400
Viewer • Updated • 221k • 48
violetxi/qwen35-4b-tmax-16turn-unfinished-trajectories
Viewer • Updated • 77 • 41
violetxi/tmax-qwen35-4b-hosted-16x8-b200
Viewer • Updated • 128 • 43
violetxi/toolathlon-qwen35-4b-base-pass1-pilot15
Viewer • Updated • 15 • 39
violetxi/tb21-eval-qwen35-action-only-20k-infra-repaired-c164-max32k-timeout2x
Viewer • Updated • 445 • 80
violetxi/tb21-eval-qwen35-action-only-40k-c164-max32k-timeout8x
Viewer • Updated • 445 • 46
violetxi/tb21-eval-qwen35-original-w005-20k-thinking-32k-timeout8x
Viewer • Updated • 445 • 55