DSpark and DFlash2 draft models for faster inference with speculative decoding
Yosef Worku Alemneh
rasyosef
AI & ML interests
Pretraining, Supervised Fine Tuning, Direct Preference Optimization, Retrieval Augmented Generation (RAG), Function Calling
Recent Activity
new activity about 15 hours ago
rasyosef/gemma-4-E2B-it-dspark:Can speculators directly train Gemma4-E2B's dflash2 and dspark?