8 16 1

Daniel Korat

danielkorat

AI & ML interests

Inference acceleration, Low-resource NLP, Few-shot learning

Recent Activity

upvoted a paper 1 day ago

FastDraft: How to Train Your Draft

updated a dataset 2 days ago

huggingface/documentation-images

New activity 2 days ago

huggingface/documentation-images:Upload method-animation.mov

View all activity

Articles

Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding

Jan 30

• 4

SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit

Dec 6, 2023

• 6

SetFit: Efficient Few-Shot Learning Without Prompts

Sep 26, 2022

• 18

Organizations

danielkorat's activity

upvoted a paper 1 day ago

FastDraft: How to Train Your Draft

Paper • 2411.11055 • Published 6 days ago • 7

updated a dataset 2 days ago

huggingface/documentation-images

Updated about 18 hours ago • 2.57M • 40

New activity in huggingface/documentation-images 2 days ago

Upload method-animation.mov

#394 opened 2 days ago by

danielkorat

New activity in huggingface/documentation-images about 1 month ago

Upload method-animation.mov

#375 opened about 1 month ago by

danielkorat

upvoted 2 articles about 1 month ago

Article

Assisted Generation: a new direction toward low-latency text generation

May 11, 2023

• 31

Article

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Apr 3

• 9

upvoted an article about 2 months ago

Article

Faster Assisted Generation with Dynamic Speculation

Oct 8

• 34

upvoted an article 3 months ago

Article

SetFit: Efficient Few-Shot Learning Without Prompts

Sep 26, 2022

• 18

upvoted a paper 4 months ago

RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation

Paper • 2408.02545 • Published Aug 5 • 33

upvoted an article 4 months ago

Article

Our Transformers Code Agent beats the GAIA benchmark!

Jul 1

• 46

upvoted an article 5 months ago

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28

• 158

upvoted 2 papers 6 months ago

Accelerating Speculative Decoding using Dynamic Speculation Length

Paper • 2405.04304 • Published May 7 • 2

Distributed Speculative Inference of Large Language Models

Paper • 2405.14105 • Published May 23 • 16

authored 2 papers 6 months ago

Accelerating Speculative Decoding using Dynamic Speculation Length

Paper • 2405.04304 • Published May 7 • 2

Distributed Speculative Inference of Large Language Models

Paper • 2405.14105 • Published May 23 • 16

New activity in lmsys/vicuna-13b-v1.3 6 months ago

Adding `safetensors` variant of this model

#5 opened 8 months ago by

SFconvertbot

New activity in lmsys/vicuna-7b-v1.3 6 months ago

Adding `safetensors` variant of this model

#4 opened 11 months ago by

SFconvertbot

New activity in bigcode/starcoder 6 months ago

Adding `safetensors` variant of this model

#112 opened 8 months ago by

SFconvertbot

upvoted 2 articles 6 months ago

Article

Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon

May 9

• 11

Article

Introducing the Open Leaderboard for Hebrew LLMs!

May 5

• 32

Daniel Korat

AI & ML interests

Recent Activity

Articles

Universal Assisted Generation: Faster Decoding with Any Assistant Model

Faster Assisted Generation with Dynamic Speculation

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding

SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit

SetFit: Efficient Few-Shot Learning Without Prompts

Organizations

danielkorat's activity

Upload method-animation.mov

Upload method-animation.mov

Assisted Generation: a new direction toward low-latency text generation

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Faster Assisted Generation with Dynamic Speculation

SetFit: Efficient Few-Shot Learning Without Prompts

Our Transformers Code Agent beats the GAIA benchmark!

Training and Finetuning Embedding Models with Sentence Transformers v3

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon

Introducing the Open Leaderboard for Hebrew LLMs!