DSpark and DFlash2 draft models for faster inference with speculative decoding
Yosef Worku Alemneh
rasyosef
P(doom) 1%
AI & ML interests
Pretraining, Supervised Fine Tuning, Direct Preference Optimization, Retrieval Augmented Generation (RAG), Function Calling
Recent Activity
updated a model about 11 hours ago
rasyosef/gemma-4-E4B-it-dspark