Continual Learning with Soft Prompt Collection Private reproducibility artifacts for distilling a mathematical reasoning RL checkpoint into a 16-token soft prompt. • 6 items • Updated 9 days ago
Continual Learning with Soft Prompt Collection Private reproducibility artifacts for distilling a mathematical reasoning RL checkpoint into a 16-token soft prompt. • 6 items • Updated 9 days ago
Continual Learning with Soft Prompt Collection Private reproducibility artifacts for distilling a mathematical reasoning RL checkpoint into a 16-token soft prompt. • 6 items • Updated 9 days ago
namezz/gptoss-swallow-full-grpo-best400-20261028 Reinforcement Learning • 21B • Updated 20 days ago • 88
namezz/gptoss-swallow-full-grpo-best400-20261028 Reinforcement Learning • 21B • Updated 20 days ago • 88