SDSB/merged_deduped_dapo_or1_dataset
Viewer
•
Updated
•
117k
•
40
Ber666
SDSB
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 16 hours ago
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain
Perspective
new activity
14 days ago
a-m-team/AM-Thinking-v1-Distilled:Which model is AM-Deepseek-R1-0528?
upvoted
a
paper
16 days ago
Training Language Models to Generate Quality Code with Program Analysis
Feedback
Organizations
