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 3 hours ago

unsloth/Llama-3.2-3B-Instruct:Up to 4x speedup with a DSpark speculative decoding draft model for Llama-3.2-3B-Instruct (35 tok/s --> 135tok/s on HumanEval )

new activity about 3 hours ago

meta-llama/Llama-3.2-3B-Instruct:Up to 4x speedup with a DSpark speculative decoding draft model for Llama-3.2-3B-Instruct (35 tok/s --> 135tok/s on HumanEval )

updated a model about 15 hours ago

rasyosef/gemma-4-E2B-it-dflash2

View all activity

Organizations

rasyosef 's papers 2

arxiv:2605.24556

arxiv:2505.19356