Models trained as a part of the "Attention Drift: What Speculative Decoding Models Learn" paper, shared for reproducing experiments.
Doğaç Eldenk
Dogacel
AI & ML interests
Inference Acceleration
Recent Activity
liked a model 2 days ago
lightseekorg/kimi-k3-dspark updated a dataset 5 days ago
Dogacel/open-perfectblend-kimi-linear-regen published a dataset 5 days ago
Dogacel/open-perfectblend-kimi-linear-regenOrganizations
None yet
models 22
Dogacel/Qwen3-8B-DSpark
2B • Updated • 59
Dogacel/specdrift-gpt-oss-20b-eagle3
0.4B • Updated • 39 • 1
Dogacel/specdrift-gpt-oss-120b-eagle3
0.4B • Updated • 46
Dogacel/specdrift-qwen3.6-35b-a3b-eagle3
0.2B • Updated • 137 • 3
Dogacel/specdrift-qwen3.6-27b-eagle3
0.6B • Updated • 143 • 1
Dogacel/paper-attention-drift-qwen35-9b-post
0.4B • Updated • 6
Dogacel/paper-attention-drift-qwen35-9b-pre
0.4B • Updated • 6
Dogacel/paper-attention-drift-gpt-20b-pre
0.3B • Updated • 20
Dogacel/paper-attention-drift-gpt-20b-post
0.3B • Updated • 7
Dogacel/paper-attention-drift-qwen3-pre
0.4B • Updated • 38
datasets 5
Dogacel/open-perfectblend-kimi-linear-regen
Viewer • Updated • 906k • 32
Dogacel/nemotron-post-training-v2-gpt-oss-20b-regen
Viewer • Updated • 931k • 51
Dogacel/nemotron-post-training-v2-gpt-oss-120b-regen
Viewer • Updated • 930k • 63 • 2
Dogacel/nemotron-post-training-v2-qwen-3.5-0.8b-regen
Viewer • Updated • 932k • 25
Dogacel/nemotron-post-training-v2-qwen-3.5-9b-regen
Viewer • Updated • 940k • 38