671 110 482

Tom Aarsen

tomaarsen

https://linkedin.com/in/tomaarsen

AI & ML interests

NLP: text embeddings, information retrieval, named entity recognition, few-shot text classification

Articles

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 55

🪆 Introduction to Matryoshka Embedding Models

Feb 23

• 46

SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit

Dec 6, 2023

• 5

🕳️ Attention Sinks in LLMs for endless fluency

Oct 9, 2023

• 6

Organizations

tomaarsen's activity

upvoted an article 1 day ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

2 days ago

• 96

upvoted 2 collections 3 days ago

embedic

Collection

Say hello to Embedić, a group of new text embedding models finetuned for the Serbian language! • 3 items • Updated 10 days ago • 5

jina-embeddings-v3

Collection

Multilingual multi-task general text embedding model • 6 items • Updated about 9 hours ago • 4

upvoted a paper 3 days ago

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

Paper • 2409.10173 • Published 3 days ago • 15

upvoted an article 4 days ago

Article

Getting Started With Embeddings

Jun 23, 2022

• 32

upvoted an article 7 days ago

Article

Fine-tuning a token classification model for legal data using Argilla and AutoTrain

•

12 days ago

• 11

upvoted a collection 8 days ago

NanoBEIR 🍺

Collection

A collection of smaller versions of BEIR datasets with 50 queries and up to 10K documents each. • 13 items • Updated 8 days ago • 2

upvoted a paper 9 days ago

OLMoE: Open Mixture-of-Experts Language Models

Paper • 2409.02060 • Published 16 days ago • 74

upvoted a paper 14 days ago

Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text

Paper • 2409.02078 • Published 16 days ago • 8

upvoted 2 collections 14 days ago

WebInstruct 🌐 Embeddings 🧱 Models

Collection

A collection of SoTA embeddings model fine-tuned on WebInstruct dataset to learn to pair instructions with its responses • 3 items • Updated 15 days ago • 11

Ruri: Japanese General Text Embeddings

Collection

18 items • Updated 7 days ago • 13

upvoted an article 26 days ago

Article

How to communicate in a Pull Request?

•

28 days ago

• 17

upvoted an article 28 days ago

Article

The 5 Most Under-Rated Tools on Hugging Face

29 days ago

• 74

upvoted 4 articles about 1 month ago

Article

Introduction to ggml

Aug 13

• 91

Article

XetHub is joining Hugging Face!

Aug 8

• 76

Article

ArabicWeb24: Creating a High Quality Arabic Web-only Pre-training Dataset

•

Aug 8

• 9

Article

2024 Security Feature Highlights

Aug 6

• 13

upvoted a collection about 2 months ago

Jais Family

Collection

The Jais Family of Models • 22 items • Updated 15 days ago • 10

upvoted 2 articles about 2 months ago

Article

Introducing BERTopic Integration with Hugging Face Hub

May 31, 2023

• 4

Article

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

Jul 31

• 58

upvoted 2 collections about 2 months ago

BRAG-v0.1

Collection

BRAG is a series of SLMs (Small Language Models) specifically trained for RAG tasks. We release models with size 1.5b, 7b and 8b. • 4 items • Updated Aug 4 • 12

Maverick Coreference Resolution

Collection

Efficient and Accurate Coreference Resolution models. • 3 items • Updated Jul 31 • 8

upvoted 4 articles 2 months ago

Article

Mixedbread 🤝 deepset: Announcing our New German/English Embedding Model

•

Jul 19

• 15

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16

• 242

Article

How we leveraged distilabel to create an Argilla 2.0 Chatbot

Jul 16

• 30

Article

Announcing New Hugging Face and Keras NLP integration

Jul 10

• 29

upvoted a paper 2 months ago

BM25S: Orders of magnitude faster lexical search via eager sparse scoring

Paper • 2407.03618 • Published Jul 4 • 10

upvoted an article 2 months ago

Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

•

Jul 5

• 85

upvoted 3 collections 3 months ago

Sentence Encoders

Collection

Collection of models and dataset for sentence encoder task • 4 items • Updated Jul 5 • 6

TrOCR Medieval HTR

Collection

This is a collection of models trained to recognize medieval scripts. • 10 items • Updated Jul 8 • 4

Arabic NLI & Semantic Similarity Datasets

Collection

The Arabic Version of SNLI and MultiNLI datasets, originally used for Natural Language Inference (NLI), may be used for finetuning embedding models. • 6 items • Updated Jun 18 • 4

upvoted 6 articles 3 months ago

Article

Image-based search engine

•

Jul 4

• 22

Article

RAG chatbot using llama3

•

Jul 7

• 66

Article

Welcome Gemma 2 - Google's new open LLM

Jun 27

• 115

Article

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡

•

Jul 9

• 34

Article

Open-source embeddings and LLMs outperform Gemini and OpenAI for Web Navigation while being faster and cheaper

•

Jun 21

• 5

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28

• 146

upvoted 5 collections 3 months ago

Graph-enhanced RAG

Collection

using knowledge graphs in RAG for grounding LLM results • 21 items • Updated 21 days ago • 7

BM25S

Collection

https://github.com/xhluca/bm25s • 15 items • Updated Jul 16 • 8

Arabic Matryoshka Embedding Models

Collection

A collection of advanced Arabic Matryoshka Embedding Models designed for efficient and high-performance Arabic NLP, available publicly on Hugging Face • 9 items • Updated Aug 2 • 8

GPL BEIR Datasets

Collection

Generative Pseudo Labeling training datasets for all domains in BEIR. • 15 items • Updated Apr 28 • 1

🦢SWIM-IR Dataset

Collection

29 million Synthetic Wikipedia-based Multilingual Retrieval Training Pairs. • 4 items • Updated Apr 28 • 7

upvoted a paper 3 months ago

Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval

Paper • 2311.05800 • Published Nov 10, 2023 • 3

upvoted a collection 3 months ago

miniMiracle dense retrievers

Collection

Low foot print multilingual retrievers, all-minilm-* equivalent. • 4 items • Updated 23 days ago • 5

upvoted an article 3 months ago

Article

Introducing the Hugging Face Embedding Container for Amazon SageMaker

Jun 7

• 13

upvoted an article 4 months ago

Article

Introducing NPC-Playground, a 3D playground to interact with LLM-powered NPCs

Jun 5

• 17

upvoted 4 collections 4 months ago

Nomic Embed Vision

Collection

Vision Encoders aligned to Nomic Embed Text making Nomic Embed multimodal! • 2 items • Updated Jun 5 • 5

Hugging Face community’s Wikimedia datasets

Collection

Wikimedia datasets created by the Hugging Face community, not Wikimedia. Sorted by Wikimedia project. • 17 items • Updated Jun 7 • 7

em🍞ing series

Collection

crispy sentence embedding family • 4 items • Updated 29 days ago • 20

Arabic NoRobots DPO Datasets

Collection

Our synthetic DPO datasets for Arabic NoRobots. • 4 items • Updated May 29 • 4

upvoted an article 4 months ago

Article

How to Fine-Tune Custom Embedding Models Using AutoTrain

•

May 30

• 10

upvoted a paper 4 months ago

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations

Paper • 2405.18392 • Published May 28 • 12

upvoted an article 4 months ago

Article

Benchmarking Text Generation Inference

May 29

• 26

upvoted 3 collections 4 months ago

sentence-transformers-from-synthetic-data

Collection

Example of using distilabel to generate synthetic triplets data for fine-tuning a Sentence Transformer model • 4 items • Updated Jun 21 • 21

Domain-specific GLiNER

Collection

6 items • Updated Jun 17 • 5

Language-specific GLiNER

Collection

5 items • Updated May 24 • 1

upvoted an article 4 months ago

Article

AI has a problem with objectifying women

•

May 24

• 54

upvoted a collection 4 months ago

C4AI Aya 23

Collection

Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. • 4 items • Updated Aug 6 • 45

upvoted 2 articles 4 months ago

Article

What is going on with AlphaFold3?

•

May 21

• 10

Article

Build AI on premise with Dell Enterprise Hub

May 21

• 17

Tom Aarsen

AI & ML interests

Articles

Welcome Gemma 2 - Google's new open LLM

Training and Finetuning Embedding Models with Sentence Transformers v3

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

🪆 Introduction to Matryoshka Embedding Models

SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit

🕳️ Attention Sinks in LLMs for endless fluency

Organizations

tomaarsen's activity

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Getting Started With Embeddings

Fine-tuning a token classification model for legal data using Argilla and AutoTrain

How to communicate in a Pull Request?

The 5 Most Under-Rated Tools on Hugging Face

Introduction to ggml

XetHub is joining Hugging Face!

ArabicWeb24: Creating a High Quality Arabic Web-only Pre-training Dataset

2024 Security Feature Highlights

Introducing BERTopic Integration with Hugging Face Hub

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

Mixedbread 🤝 deepset: Announcing our New German/English Embedding Model

SmolLM - blazingly fast and remarkably powerful

How we leveraged distilabel to create an Argilla 2.0 Chatbot

Announcing New Hugging Face and Keras NLP integration

ColPali: Efficient Document Retrieval with Vision Language Models 👀

Image-based search engine

RAG chatbot using llama3

Welcome Gemma 2 - Google's new open LLM

BM25 for Python: Achieving high performance while simplifying dependencies with *BM25S*⚡

Open-source embeddings and LLMs outperform Gemini and OpenAI for Web Navigation while being faster and cheaper

Training and Finetuning Embedding Models with Sentence Transformers v3

Introducing the Hugging Face Embedding Container for Amazon SageMaker

Introducing NPC-Playground, a 3D playground to interact with LLM-powered NPCs

How to Fine-Tune Custom Embedding Models Using AutoTrain

Benchmarking Text Generation Inference

AI has a problem with objectifying women

What is going on with AlphaFold3?

Build AI on premise with Dell Enterprise Hub

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡