Data and model for the When Vision Speaks for Sound. Includes SFT and DPO training data, evaluation data and trained checkpoints.
Xiaofei Wen
Rakancorle1
AI & ML interests
None yet
Organizations
None yet
models 8
Rakancorle1/wvs-thud-model
32B • Updated • 11 • 2
Rakancorle1/FoodGuard_qwenguard_4b_4k
196k • Updated • 4
Rakancorle1/policyguard-4B-SS
Text Generation • 4B • Updated • 34 •
Rakancorle1/FoodGuard_qwenguard_4k
Text Generation • 308k • Updated • 5
Rakancorle1/PolicyGuard-4B
Text Classification • 196k • Updated • 83 • 3
Rakancorle1/ThinkGuard
Text Classification • 8B • Updated • 248 • 4
Rakancorle1/ThinkGuard_27k_3epochs
Updated
Rakancorle1/laaj_15k_label_only
Updated • 1
datasets 9
Rakancorle1/hans-10k
Viewer • Updated • 20.8k • 53
Rakancorle1/vggsync-3k
Viewer • Updated • 3k • 40
Rakancorle1/thud-eval
Viewer • Updated • 710 • 45
Rakancorle1/hans-sft-4k
Viewer • Updated • 3.83k • 28 • 1
Rakancorle1/policyguardbench-ss
Viewer • Updated • 60k • 10
Rakancorle1/Policy_Traj_LODO
Viewer • Updated • 250k • 40
Rakancorle1/Policy_Trajectories_TopNactions
Viewer • Updated • 25.4k • 23
Rakancorle1/Policy_Traj_0826_30k_train
Viewer • Updated • 24k • 12
Rakancorle1/PolicyGuardBench
Viewer • Updated • 60k • 54 • 5