mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-140 8B • Updated Oct 14 • 4
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-190 8B • Updated Oct 14 • 9
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-220 8B • Updated Oct 14 • 3
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-250 8B • Updated Oct 14 • 4
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic-sampling-clip-high-step-180 8B • Updated Oct 14 • 3
mlfoundations-cua-dev/qwen3_vl_30b_grpo-stage-1-on-103k-filtered-data-dynamic-sampling-partial-data Updated Oct 14
mlfoundations-cua-dev/qwen2_5vl_7b_110k_plus_agentnet_clicks_lr_1_0e-06_z3_4nodes 8B • Updated Oct 12 • 4
mlfoundations-cua-dev/ubuntu_traj_rl_bbox_max_500_samples_max_turns_10 Viewer • Updated 16 days ago • 1k • 52
mlfoundations-cua-dev/63k-nores-jedi-5k-refusal-train-subsample Viewer • Updated 27 days ago • 1k • 30
mlfoundations-cua-dev/qwen3-resize-easyr1-110k-bbox0p05-remove-pixmo-uground-seeclick-normalized Viewer • Updated Oct 13 • 101k • 257