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
new activity about 12 hours ago
Dogacel/Qwen3-8B-DSpark:Performance? updated a model about 12 hours ago
Dogacel/Qwen3-8B-DSpark published a model about 12 hours ago
Dogacel/Qwen3-8B-DSparkOrganizations
None yet