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 about 14 hours ago
violetxi/qwen35-9b-wmrl-v4-c2-p6 published a model about 14 hours ago
violetxi/qwen35-9b-wmrl-v4-c2-p6 updated a model about 15 hours ago
violetxi/qwen35-9b-wmrl-v4-m3-obsdocOrganizations
models 86
violetxi/qwen35-9b-wmrl-v4-c2-p6
10B • Updated
violetxi/qwen35-9b-wmrl-v4-m3-obsdoc
10B • Updated
violetxi/qwen35-9b-wmrl-v4-m2-abstain
10B • Updated
violetxi/qwen35-9b-wmrl-v4-m1-mixture
10B • Updated
violetxi/qwen35-9b-wmrl-v4-c1-b5v4
10B • Updated
violetxi/qwen35-9b-wmrl-v4-c4-action
10B • Updated
violetxi/qwen35-9b-wmrl-v4-lrsmoke-5e6
10B • Updated • 15
violetxi/qwen35-9b-wmrl-v4-lrsmoke-1e5
10B • Updated • 15
violetxi/chess-5epochs-block-mtp-full-bptt-20m
Updated
violetxi/chess-5epochs-block-mtp-truncated-bptt-20m
Updated
datasets 210
violetxi/ch-stagec-trajectory-pool-qwen3.5-4b
Viewer • Updated • 14.9k • 35
violetxi/ch-trajectory-pool-qwen3.5-4b
Viewer • Updated • 1.38k • 32
violetxi/ch-pilot-rollouts-qwen3.5-9b
Viewer • Updated • 296 • 46
violetxi/ch-pilot-rollouts-qwen3.5-35b-a3b
Viewer • Updated • 261 • 51
violetxi/chess-20m-tactical-eval-traces
Viewer • Updated • 31.1k • 89
violetxi/chess_puzzle_training_datasets_lt-2400
Viewer • Updated • 221k • 60
violetxi/qwen35-4b-tmax-16turn-unfinished-trajectories
Viewer • Updated • 77 • 51
violetxi/tmax-qwen35-4b-hosted-16x8-b200
Viewer • Updated • 128 • 56
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 • 83