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
published a model about 3 hours ago
namezz/soft-prompt-interpretability-six-pairs upvoted a paper 8 days ago
Bellman Policy Optimization published a dataset 13 days ago
namezz/soft-prompt-experiments-archive-20260918Organizations
-
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-7b-instruct
Text Generation • 8B • Updated • 9 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 6 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-0.5b-instruct
Text Generation • 0.5B • Updated • 12 -
namezz/lvm-instruct-0327-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 12
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 • 9 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 6 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-0.5b-instruct
Text Generation • 0.5B • Updated • 12 -
namezz/lvm-instruct-0327-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 12
models 18
namezz/soft-prompt-interpretability-six-pairs
Updated
namezz/deepscaler-1p5b-soft-prompt-len16
Updated
namezz/lvm-math-0408-a-qwen3-30b-a3b-instruct-b-qwen3-1.7b-base
Text Generation • 2B • Updated • 9
namezz/lvm-math-0402-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 9
namezz/lvm-instruct-0327-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 12
namezz/lvm-instruct-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
2B • Updated • 5
namezz/lvm-a-qwen3-30b-a3b-instruct-b-qwen3-1.7b-base
2B • Updated • 8
namezz/lvm-a-qwen2.5-vl-7b-instruct-b-qwen2.5-vl-3b-instruct
Image-Text-to-Text • 4B • Updated • 6
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-7b-instruct
Text Generation • 8B • Updated • 9
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 6
datasets 8
namezz/soft-prompt-experiments-archive-20260918
Viewer • Updated • 169 • 480
namezz/deepscaler-1p5b-teacher-rollouts-broad
Updated • 15
namezz/deepscaler-1p5b-teacher-rollouts
Updated • 17
namezz/LenVM-Data
Preview • Updated • 498
namezz/LenVM-Data-Old
Preview • Updated • 340
namezz/LenVM_Data
Viewer • Updated • 8.19k • 8
namezz/lenvm_data_old
Preview • Updated • 39
namezz/Checklist
Viewer • Updated • 8.63k • 87 • 1