2 9 5

Ofir Zafrir

ofirzaf

AI & ML interests

Sparsity, Qunatization, Model Compression

Recent Activity

liked a model 3 days ago

OpenVINO/Qwen3-pruned-6L-from-0.6B-int8-ov

upvoted an article 21 days ago

Breaking Language Barriers in Mathematical AI: Introducing Hebrew Math Tutor

liked a model 3 months ago

OpenVINO/Phi-3-mini-FastDraft-50M-int8-ov

View all activity

Organizations

liked a model 3 days ago

OpenVINO/Qwen3-pruned-6L-from-0.6B-int8-ov

Updated 4 days ago • 20 • 1

upvoted an article 21 days ago

Article

Breaking Language Barriers in Mathematical AI: Introducing Hebrew Math Tutor

•

21 days ago

• 2

liked 2 models 3 months ago

OpenVINO/Phi-3-mini-FastDraft-50M-int8-ov

Updated Dec 16, 2024 • 36 • 5

OpenVINO/Phi-4-mini-FastDraft-120M-int8-ov

Updated May 8 • 17 • 2

upvoted 2 articles 6 months ago

Article

Introducing HELMET

and 6 others •

Apr 16

• 37

Article

Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques

and 8 others •

Mar 24

• 20

upvoted a paper 7 months ago

SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models

Paper • 2502.09390 • Published Feb 13 • 17

upvoted a collection 8 months ago

Speculative Decoding Draft Models

Collection

Collection of OpenVINO optimized efficient draft models for speculative decoding • 4 items • Updated 13 days ago • 9

liked a model 8 months ago

OpenVINO/Llama-3.1-8B-Instruct-FastDraft-150M-int8-ov

Updated Dec 16, 2024 • 2.02k • 7

upvoted an article 8 months ago

Article

A Chatbot on your Laptop: Phi-2 on Intel Meteor Lake

and 5 others •

Mar 20, 2024

• 7

authored 2 papers 10 months ago

Q8BERT: Quantized 8Bit BERT

Paper • 1910.06188 • Published Oct 14, 2019 • 2

FastDraft: How to Train Your Draft

Paper • 2411.11055 • Published Nov 17, 2024 • 11

upvoted a paper 10 months ago

FastDraft: How to Train Your Draft

Paper • 2411.11055 • Published Nov 17, 2024 • 11

upvoted a paper about 1 year ago