Private reproducibility artifacts for distilling a mathematical reasoning RL checkpoint into a 16-token soft prompt.
zhenzhang
namezz
AI & ML interests
None yet
Recent Activity
updated a model 6 days ago
namezz/soft-prompt-interpretability-six-pairs published a model 19 days ago
namezz/soft-prompt-interpretability-six-pairs upvoted a paper 27 days ago
Bellman Policy OptimizationOrganizations
-
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-7b-instruct
Text Generation • 8B • Updated • 15 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 9 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-0.5b-instruct
Text Generation • 0.5B • Updated • 8 -
namezz/lvm-instruct-0327-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 8
Private reproducibility artifacts for distilling a mathematical reasoning RL checkpoint into a 16-token soft prompt.
-
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-7b-instruct
Text Generation • 8B • Updated • 15 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 9 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-0.5b-instruct
Text Generation • 0.5B • Updated • 8 -
namezz/lvm-instruct-0327-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 8
Checklist