Per-neuron sigmoid gates on Qwen3 FFN neurons to disentangle factual knowledge from reasoning.
HyunseokLee
hyunseoki
AI & ML interests
None yet
Recent Activity
updated a model 13 days ago
hyunseoki/qwen3-0.6b-moe-prune-checkpoints published a model 13 days ago
hyunseoki/qwen3-0.6b-moe-prune-checkpoints updated a collection 17 days ago
Qwen3 Lambda Gates — Knowledge/Reasoning DisentanglementOrganizations
Grouped HF exports for the verl math transfer experiments.
-
hyunseoki/verl-math-transfer-7bi-to-7bi-v2
Text Generation • 8B • Updated • 39 -
hyunseoki/verl-math-transfer-7bi-to-3bi-fix03
Text Generation • 8B • Updated • 90 -
hyunseoki/verl-math-transfer-7bi-to-3bi-fix07-pool7to1
Text Generation • 8B • Updated • 84 -
hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1
Text Generation • 8B • Updated • 45
Per-neuron sigmoid gates on Qwen3 FFN neurons to disentangle factual knowledge from reasoning.
Grouped HF exports for the verl math transfer experiments.
-
hyunseoki/verl-math-transfer-7bi-to-7bi-v2
Text Generation • 8B • Updated • 39 -
hyunseoki/verl-math-transfer-7bi-to-3bi-fix03
Text Generation • 8B • Updated • 90 -
hyunseoki/verl-math-transfer-7bi-to-3bi-fix07-pool7to1
Text Generation • 8B • Updated • 84 -
hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1
Text Generation • 8B • Updated • 45
models 37
hyunseoki/qwen3-0.6b-moe-prune-checkpoints
Updated
hyunseoki/qwen3-1.7b-lambda-gates-chat
Updated
hyunseoki/qwen3-0.6b-lambda-gates-chat
Updated
hyunseoki/qwen3-0.6b-lambda-gates-nke
Updated
hyunseoki/qwen3-0.6b-lambda-gates-baseline
Updated
hyunseoki/verl-math-transfer-7bi-to-3bi-fix05-pool7to1
Text Generation • 8B • Updated • 38
hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1
Text Generation • 8B • Updated • 45
hyunseoki/verl-math-transfer-7bi-to-3bi-fix07-pool7to1
Text Generation • 8B • Updated • 84
hyunseoki/verl-math-transfer-7bi-to-3bi-fix03
Text Generation • 8B • Updated • 90
hyunseoki/verl-math-transfer-7bi-to-7bi-v2
Text Generation • 8B • Updated • 39
datasets 15
hyunseoki/memory-reasoning-split-eval-sets
Preview • Updated • 83
hyunseoki/popqa-mini-ner-knowledge-masks
Preview • Updated • 52
hyunseoki/qwen3-0p6b-openthoughts-self-distill-10k
Preview • Updated • 71
hyunseoki/qwen3-0p6b-openthoughts-self-distill-1k
Preview • Updated • 90
hyunseoki/openthoughts3-dedup-index
Updated • 53
hyunseoki/numina-math-10k-seed13
Viewer • Updated • 11k • 9
hyunseoki/prefixgen_MATH
Viewer • Updated • 60k • 4
hyunseoki/math_train_1k
Viewer • Updated • 1k • 6
hyunseoki/gsm8k_cot_zeroshot_second
Viewer • Updated • 3.33k • 8
hyunseoki/gsm8k_cot_zeroshot_third
Viewer • Updated • 1.63k • 10