CSEG reward models (SFT, GRPO, SFT-GRPO at 4B and 8B) and CSEG-Bench.
Haochen Zhao
VectorZhao
AI & ML interests
None yet
Recent Activity
published a model 7 days ago
VectorZhao/CSEG-RM-GRPO-8B published a model 7 days ago
VectorZhao/CSEG-RM-SFT-GRPO-8B published a model 7 days ago
VectorZhao/CSEG-RM-SFT-GRPO-4BOrganizations
models 15
VectorZhao/CSEG-RM-GRPO-8B
Text Generation • 8B • Updated • 2
VectorZhao/CSEG-RM-SFT-GRPO-8B
Text Generation • 8B • Updated • 3
VectorZhao/CSEG-RM-SFT-GRPO-4B
Text Generation • 4B • Updated • 4
VectorZhao/CSEG-RM-GRPO-4B
Text Generation • 4B • Updated • 1
VectorZhao/CSEG-RM-SFT-8B
Text Generation • 8B • Updated • 5
VectorZhao/CSEG-RM-SFT-4B
Text Generation • 4B • Updated • 5
VectorZhao/phi3.5v-open-o1
Updated
VectorZhao/a2c-PandaReachDense-v3
Reinforcement Learning • Updated • 8
VectorZhao/ppo-SnowballTarget
Reinforcement Learning • Updated • 38
VectorZhao/Reinforce-CartPole-v1
Reinforcement Learning • Updated
datasets 6
VectorZhao/CSEG-Bench
Viewer • Updated • 1.16k • 73
VectorZhao/DotsOnCurve
Viewer • Updated • 100 • 7
VectorZhao/countbench-large
Viewer • Updated • 10k • 32
VectorZhao/countbench-medium
Viewer • Updated • 10k • 32
VectorZhao/countbench-mini
Viewer • Updated • 10k • 33
VectorZhao/LinePlotIntersection
Viewer • Updated • 2.9k • 6