Yosef Worku Alemneh

rasyosef

AI & ML interests

Pretraining, Supervised Fine Tuning, Direct Preference Optimization, Retrieval Augmented Generation (RAG), Function Calling

Recent Activity

new activity 1 day ago

Qwen/Qwen3-1.7B:Qwen3-1.7B-DSpark: A DSpark draft model for Qwen3-1.7B (upto 3x speedup; 220 --> 646 tokens/sec)

updated a model 1 day ago

rasyosef/Qwen3.5-2B-DSpark

updated a model 1 day ago

rasyosef/Qwen3-1.7B-DSpark

View all activity

Organizations

New activity in Qwen/Qwen3-1.7B 1 day ago

Qwen3-1.7B-DSpark: A DSpark draft model for Qwen3-1.7B (upto 3x speedup; 220 --> 646 tokens/sec)

#24 opened 1 day ago by

rasyosef

New activity in google/gemma-4-E2B-it-assistant 6 days ago

Up to 3.74x faster inference with a DFlash2 speculative decoding draft model for gemma-4-E2B-it (167 --> 626 tokens/s)

#2 opened 6 days ago by

rasyosef

New activity in google/gemma-4-E2B-it 6 days ago

3.7x faster inference with a DSpark (speculative decoding) draft model for gemma-4-E2B-it

#49 opened 7 days ago by

rasyosef

Up to 3.74x faster inference with DFlash2 speculative decoding draft model for gemma-4-E2B-it (167 --> 626 tokens/s)

#50 opened 6 days ago by

rasyosef

New activity in unsloth/Llama-3.2-3B-Instruct 7 days ago

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

#2 opened 7 days ago by

rasyosef

New activity in meta-llama/Llama-3.2-3B-Instruct 7 days ago

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

#314 opened 7 days ago by

rasyosef

New activity in unsloth/Llama-3.2-1B-Instruct 26 days ago

A DSpark draft model for Llama-3.2-1B-Instruct (1.5x - 2.7x higher throughput)

#4 opened 26 days ago by

rasyosef

New activity in meta-llama/Llama-3.2-1B-Instruct 26 days ago

A DSpark draft model for Llama-3.2-1B-Instruct (1.5x - 2.7x higher throughput)

#198 opened 26 days ago by

rasyosef

New activity in yosefw/Qwen3-0.6B-DSpark-v2 about 1 month ago

Create README.md

#1 opened about 1 month ago by

rasyosef

New activity in yosefw/Qwen3-0.6B-DSpark about 1 month ago

Update README.md

#1 opened about 1 month ago by

rasyosef

New activity in rasyosef/colbert-amharic-base 4 months ago

Improve model card: update pipeline tag, add paper and code links

🤗 1

#1 opened 4 months ago by

nielsr

New activity in rasyosef/reranker-amharic-medium 4 months ago

Improve model card: add paper, code links and citation

🤗 1

#2 opened 4 months ago by

nielsr

New activity in rasyosef/embedding-amharic-medium 4 months ago

Add paper and code links, update pipeline tag

🤗 1

#1 opened 4 months ago by

nielsr

New activity in rasyosef/splade-amharic-base 4 months ago

Improve model card: add paper link, code link, and update pipeline tag

🤗 1

#1 opened 4 months ago by

nielsr

New activity in rasyosef/reranker-amharic-base 4 months ago

Add paper and code links to model card

🤗 1

#1 opened 4 months ago by

nielsr

New activity in rasyosef/colbert-amharic-medium 4 months ago

Improve model card: update pipeline tag and add paper/code links

🤗 1

#1 opened 4 months ago by

nielsr

New activity in rasyosef/splade-amharic-medium 4 months ago

Improve model card: update pipeline tag and add paper/code links

🤗 1

#1 opened 4 months ago by

nielsr

New activity in rasyosef/Amharic-Passage-Retrieval-Dataset-V2 4 months ago

Add paper link, GitHub link, and task category

🤗 1

#2 opened 4 months ago by

nielsr

New activity in naver/splade-v3 about 1 year ago

SPLADE-Index python package: An ultra-fast search index for SPLADE sparse retrieval models

🚀 1

#8 opened about 1 year ago by

rasyosef

New activity in cross-encoder/ms-marco-MiniLM-L6-v2 about 1 year ago

MS Marco Dev number of queries and documents

#15 opened about 1 year ago by

rasyosef

Yosef Worku Alemneh

AI & ML interests

Recent Activity

Organizations

rasyosef's activity

Qwen3-1.7B-DSpark: A DSpark draft model for Qwen3-1.7B (upto 3x speedup; 220 --> 646 tokens/sec)

Up to 3.74x faster inference with a DFlash2 speculative decoding draft model for gemma-4-E2B-it (167 --> 626 tokens/s)

3.7x faster inference with a DSpark (speculative decoding) draft model for gemma-4-E2B-it

Up to 3.74x faster inference with DFlash2 speculative decoding draft model for gemma-4-E2B-it (167 --> 626 tokens/s)

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

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

A DSpark draft model for Llama-3.2-1B-Instruct (1.5x - 2.7x higher throughput)

A DSpark draft model for Llama-3.2-1B-Instruct (1.5x - 2.7x higher throughput)

Create README.md

Update README.md

Improve model card: update pipeline tag, add paper and code links

Improve model card: add paper, code links and citation

Add paper and code links, update pipeline tag

Improve model card: add paper link, code link, and update pipeline tag

Add paper and code links to model card

Improve model card: update pipeline tag and add paper/code links

Improve model card: update pipeline tag and add paper/code links

Add paper link, GitHub link, and task category

SPLADE-Index python package: An ultra-fast search index for SPLADE sparse retrieval models

MS Marco Dev number of queries and documents