OVD paper checkpoints: 1-data and 128-data training, Full response, High-entropy suffix, Random suffix, and RLVR baselines.
Jing Xiong
menik1126
AI & ML interests
Natural Language Processing
Recent Activity
updated a collection 4 days ago
OVD published a model 4 days ago
menik1126/OVD-Web-Qwen2.5-3B-reject5-Step200 updated a model 4 days ago
menik1126/OVD-Web-Qwen2.5-3B-reject5-Step200