Private reproducibility artifacts for distilling a mathematical reasoning RL checkpoint into a 16-token soft prompt.
zhenzhang PRO
namezz
AI & ML interests
None yet
Recent Activity
updated a dataset about 2 hours ago
namezz/continual-learning-with-soft-prompt-data updated a collection about 13 hours ago
Continual Learning with Soft Prompt published a dataset about 21 hours ago
namezz/continual-learning-with-soft-prompt-dataOrganizations
-
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-7b-instruct
Text Generation • 8B • Updated • 17 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 7 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-0.5b-instruct
Text Generation • 0.5B • Updated • 9 -
namezz/lvm-instruct-0327-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 5
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 • 17 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 7 -
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-0.5b-instruct
Text Generation • 0.5B • Updated • 9 -
namezz/lvm-instruct-0327-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 5
models 19
namezz/gptoss-swallow-full-grpo-best400-20261028
Reinforcement Learning • 21B • Updated • 48
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 • 10
namezz/lvm-math-0402-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 10
namezz/lvm-instruct-0327-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct
Text Generation • 2B • Updated • 5
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 • 7
namezz/lvm-a-qwen2.5-vl-7b-instruct-b-qwen2.5-vl-3b-instruct
Image-Text-to-Text • 4B • Updated • 2
namezz/lvm-a-qwen2.5-7b-instruct-b-qwen2.5-7b-instruct
Text Generation • 8B • Updated • 17
datasets 13
namezz/continual-learning-with-soft-prompt-data
Updated
namezz/m2rl-issue18-code-transfer-public-20261030
Updated • 90
namezz/gptoss-full-sp-rl-stopped-20261028
Preview • Updated • 332
namezz/seer-agent-traces
Updated • 251
namezz/agent-training-backup-20261019
Viewer • Updated • 600 • 245
namezz/soft-prompt-experiments-archive-20260918
Viewer • Updated • 169 • 596
namezz/deepscaler-1p5b-teacher-rollouts-broad
Updated • 473
namezz/deepscaler-1p5b-teacher-rollouts
Updated • 17
namezz/LenVM-Data
Preview • Updated • 106
namezz/LenVM-Data-Old
Preview • Updated • 135