621 76 323

Tom Aarsen

tomaarsen

https://linkedin.com/in/tomaarsen

tomaarsen

AI & ML interests

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

Articles

Training and Finetuning Embedding Models with Sentence Transformers v3

30 days ago

• 103

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Apr 3

• 6

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 43

Organizations

tomaarsen's activity

upvoted an article 2 days ago

Article

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

•

about 15 hours ago

• 21

upvoted 2 articles 5 days ago

Article

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

•

5 days ago

• 4

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

30 days ago

• 103

upvoted a collection 7 days ago

Graph-enhanced RAG

Collection

using knowledge graphs in RAG for grounding LLM results • 18 items • Updated 5 days ago • 3

upvoted a collection 8 days ago

BM25S Indices

Collection

https://github.com/xhluca/bm25s • 14 items • Updated 8 days ago • 7

upvoted a collection 9 days ago

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 • 6 items • Updated about 22 hours ago • 2

upvoted 2 collections 10 days ago

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 10 days 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 15 days ago

miniMiracle dense retrievers

Collection

Low foot print multilingual retrievers, all-minilm-* equivalent. • 3 items • Updated 18 days ago • 5

upvoted an article 19 days ago

Article

Introducing the Hugging Face Embedding Container for Amazon SageMaker

20 days ago

• 9

upvoted an article 21 days ago

Article

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

22 days ago

• 12

upvoted a collection 21 days ago

Nomic Embed Vision

Collection

Vision Encoders aligned to Nomic Embed Text making Nomic Embed multimodal! • 2 items • Updated 21 days ago • 4

upvoted 3 collections 26 days ago

Hugging Face community’s Wikimedia datasets

Collection

Wikimedia datasets created by the Hugging Face community, not Wikimedia. Sorted by Wikimedia project. • 17 items • Updated 19 days ago • 6

em🍞ing series

Collection

crispy sentence embedding family • 3 items • Updated Mar 28 • 18

Arabic NoRobots DPO Datasets

Collection

Our synthetic DPO datasets for Arabic NoRobots. • 4 items • Updated 28 days ago • 4

upvoted an article 27 days ago

Article

How to Fine-Tune Custom Embedding Models Using AutoTrain

•

27 days ago

• 10

upvoted a paper 28 days ago

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations

Paper • 2405.18392 • Published 29 days ago • 12

upvoted an article 28 days ago

Article

Benchmarking Text Generation Inference

29 days ago

• 24

upvoted a collection 28 days 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 5 days ago • 20

upvoted 2 collections about 1 month ago

Domain-specific GLiNER

Collection

6 items • Updated 9 days ago • 2

Language-specific GLiNER

Collection

5 items • Updated May 24 • 1

upvoted an article about 1 month ago

Article

AI has a problem with objectifying women

•

May 24

• 54

upvoted a collection about 1 month ago

C4AI Aya 23

Collection

Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. • 3 items • Updated May 23 • 37

upvoted 2 articles about 1 month ago

Article

What is going on with AlphaFold3?

•

May 21

• 8

Article

Build AI on premise with Dell Enterprise Hub

May 21

• 13

upvoted a collection about 1 month ago

Pokemons

Collection

5 items • Updated May 1 • 2

upvoted 2 papers about 1 month ago

INDUS: Effective and Efficient Language Models for Scientific Applications

Paper • 2405.10725 • Published May 17 • 23

ParaNames 1.0: Creating an Entity Name Corpus for 400+ Languages using Wikidata

Paper • 2405.09496 • Published May 15 • 3

upvoted 2 articles about 1 month ago

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

May 14

• 152

Article

2024-04-22 - Hub Incident Post Mortem

•

May 17

• 17

upvoted 3 collections about 1 month ago

MS MARCO Mined Triplets

Collection

These datasets contain MS MARCO Triplets gathered by mining hard negatives using various models. Each dataset has various subsets. • 14 items • Updated May 21 • 6

Parallel Sentences Datasets

Collection

These datasets all have "english" and "non_english" columns for numerous datasets. They can be used to make embedding models multilingual. • 13 items • Updated 8 days ago • 4

Embedding Model Datasets

Collection

A curated subset of the datasets that work out of the box with Sentence Transformers: https://huggingface.co/datasets?other=sentence-transformers • 66 items • Updated 5 days ago • 37

upvoted a paper about 1 month ago

Piccolo2: General Text Embedding with Multi-task Hybrid Loss Training

Paper • 2405.06932 • Published May 11 • 15

upvoted an article about 1 month ago

Article

Hugging Face x LangChain : A new partner package in LangChain

May 14

• 82

upvoted a collection about 1 month ago

NuNerZero - Zero Shot NER

Collection

The best compact Zero-Shot NER models with MIT license • 4 items • Updated 1 day ago • 14

upvoted 4 articles about 2 months ago

Article

Train Custom Models on Hugging Face Spaces with AutoTrain SpaceRunner

•

May 9

• 7

Article

⚗️ 🧑🏼‍🌾 Let's grow some Domain Specific Datasets together

•

Apr 29

• 27

Article

🧑‍⚖️ "Replacing Judges with Juries" using distilabel

•

May 3

• 15

Article

Synthetic data: save money, time and carbon with open source

Feb 16

• 32

upvoted 2 papers about 2 months ago

What matters when building vision-language models?

Paper • 2405.02246 • Published May 3 • 90

Model Merging by Uncertainty-Based Gradient Matching

Paper • 2310.12808 • Published Oct 19, 2023 • 6

upvoted an article about 2 months ago

Article

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Apr 22

• 75

upvoted 3 collections about 2 months ago

🇫🇷 Cross-encoder rerankers

Collection

A collection of cross-encoder reranking models in French. • 31 items • Updated May 6 • 3

🇫🇷 Single-vector dense bi-encoders

Collection

A collection of single-vector dense representation models in French. • 16 items • Updated 25 days ago • 2

Llama3-ChatQA-1.5

Collection

Llama3-ChatQA-1.5 models excel at conversational question answering (QA) and retrieval-augmented generation (RAG). • 6 items • Updated 12 days ago • 37

upvoted an article about 2 months ago

Article

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation

Apr 29

• 70

upvoted an article 2 months ago

Article

🦙⚗️ Using Llama3 and distilabel to build fine-tuning datasets

•

22 days ago

• 63

upvoted a collection 2 months ago

Arctic

Collection

A collection of pre-trained dense-MoE Hybrid transformer models • 2 items • Updated Apr 24 • 20

upvoted a paper 2 months ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22 • 239

upvoted a collection 2 months ago

Phi-3

Collection

Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. • 22 items • Updated 27 days ago • 345

upvoted a paper 2 months ago

LongEmbed: Extending Embedding Models for Long Context Retrieval

Paper • 2404.12096 • Published Apr 18 • 2

upvoted an article 2 months ago

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18

• 253

upvoted a collection 2 months ago

Arctic-embed

Collection

A collection of text embedding models optimized for retrieval accuracy and efficiency • 5 items • Updated Apr 17 • 11

upvoted 2 articles 2 months ago

Article

Mergoo: Efficiently Build Your Own MoE LLM

•

23 days ago

• 37

Article

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 43

upvoted an article 3 months ago

Article

Hugging Face partners with Wiz Research to Improve AI Security

Apr 4

• 11

upvoted a collection 3 months ago

Vector-io compatible Datasets

Collection

These datasets can be loaded into your vector database with a single line bash command • 14 items • Updated Mar 29 • 3

upvoted a paper 4 months ago

GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer

Paper • 2311.08526 • Published Nov 14, 2023 • 8

Tom Aarsen

AI & ML interests

Articles

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

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

PaliGemma – Google's Cutting-Edge Open Vision Language Model

2024-04-22 - Hub Incident Post Mortem

Hugging Face x LangChain : A new partner package in LangChain

Train Custom Models on Hugging Face Spaces with AutoTrain SpaceRunner

⚗️ 🧑🏼‍🌾 Let's grow some Domain Specific Datasets together

🧑‍⚖️ "Replacing Judges with Juries" using distilabel

Synthetic data: save money, time and carbon with open source

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation

🦙⚗️ Using Llama3 and distilabel to build fine-tuning datasets

Welcome Llama 3 - Meta's new open LLM

Mergoo: Efficiently Build Your Own MoE LLM

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Hugging Face partners with Wiz Research to Improve AI Security

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