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
published a model about 1 hour ago
rasyosef/K2-Horizon-32B-DSpark updated a dataset about 2 hours ago
rasyosef/open-perfectblend_K2-Horizon-32B-NVFP4 published a dataset 1 day ago
rasyosef/open-perfectblend_K2-Horizon-32B-NVFP4