High-quality math reasoning datasets in VERL format
sungyub kim
sungyub
AI & ML interests
LLM
Recent Activity
authored a paper 1 day ago
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization authored a paper 1 day ago
LANTERN: Accelerating Visual Autoregressive Models with Relaxed
Speculative Decoding liked a Space 11 days ago
FineEnvs/multi-harness-rlOrganizations
None yet
models 0
None public yet
datasets 27
sungyub/deepscaler-preview-verl
Viewer • Updated • 38k • 892
sungyub/qa-verl-unified
Viewer • Updated • 86.4k • 60
sungyub/docqa-rl-verl
Viewer • Updated • 3.6k • 21
sungyub/code-verl-unified
Viewer • Updated • 959k • 592 • 2
sungyub/codev-r1-verl
Viewer • Updated • 3.13k • 21
sungyub/math-verl-unified
Viewer • Updated • 2.27M • 130 • 2
sungyub/dapo-math-17k-verl
Viewer • Updated • 17.2k • 148
sungyub/skywork-or1-math-verl
Viewer • Updated • 103k • 21
sungyub/orz-math-72k-verl
Viewer • Updated • 46.4k • 93
sungyub/deepmath-103k-verl
Viewer • Updated • 102k • 28