553 29 169

Tom Aarsen

tomaarsen

https://linkedin.com/in/tomaarsen

tomaarsen

AI & ML interests

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

Articles

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Apr 3

• 5

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 29

Organizations

tomaarsen's activity

liked 2 datasets 1 day ago

tarudesu/ViHealthQA

Viewer • Updated Nov 28, 2023 • 218 • 5

WhereIsAI/github-issue-similarity

Viewer • Updated 1 day ago • 91 • 2

liked a model 1 day ago

WhereIsAI/UAE-Code-Large-V1

Feature Extraction • Updated 1 day ago • 8 • 2

liked a model 2 days ago

COCO0414/DNF-bge-m3

liked 2 datasets 2 days ago

sentence-transformers/simple-wiki

Viewer • Updated 4 days ago • 4 • 1

avramandrei/histnero

Viewer • Updated 2 days ago • 11 • 4

liked a dataset 6 days ago

sergeyvi4ev/questions_to_evidence_triplets

Viewer • Updated 12 days ago • 1

liked a dataset 7 days ago

Mihaiii/qa-assistant

Viewer • Updated 7 days ago • 24 • 3

liked 2 models 8 days ago

manu/sentence_croissant_alpha_v0.3

akiFQC/bert-base-japanese-v3_nli-jsnli-jnli-jsick

Zero-Shot Classification • Updated 8 days ago • 11 • 1

liked a dataset 9 days ago

stanfordnlp/snli

Viewer • Updated Mar 6 • 4.3k • 51

liked a space 10 days ago

Running

144

📈

Snowflake Arctic St Demo

liked 2 models 10 days ago

Snowflake/snowflake-arctic-instruct

Text Generation • Updated 8 days ago • 12.9k • 299

Snowflake/snowflake-arctic-base

Text Generation • Updated 8 days ago • 86 • 59

liked a space 11 days ago

Running

📕

Ratchet + Phi

liked 2 models 11 days ago

microsoft/Phi-3-mini-128k-instruct

Text Generation • Updated 2 days ago • 252k • 1.07k

urchade/gliner_multi_pii-v1

Token Classification • Updated 14 days ago • 4.89k • 14

liked 2 models 15 days ago

meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • Updated 10 days ago • 1.09M • 1.77k

meta-llama/Meta-Llama-3-8B

Text Generation • Updated 10 days ago • 708k • 3.16k

liked 2 models 16 days ago

jinaai/jina-reranker-v1-turbo-en

Feature Extraction • Updated 16 days ago • 6.57k • 22

jinaai/jina-reranker-v1-tiny-en

Feature Extraction • Updated 16 days ago • 2.76k • 7

liked a model 17 days ago

mistralai/Mixtral-8x22B-Instruct-v0.1

Text Generation • Updated 11 days ago • 46.8k • 505

liked a model 18 days ago

HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1

Text Generation • Updated 16 days ago • 5.06k • 222

liked 2 datasets 24 days ago

urchade/pile-mistral-v0.1

Updated Mar 18 • 7 • 3

multilingual/orca_dpo_pairs

Viewer • Updated Apr 3 • 411 • 13

liked 3 models 24 days ago

mistral-community/Mixtral-8x22B-v0.1

Text Generation • Updated 17 days ago • 48.6k • 663

jetmoe/jetmoe-8b

Text Generation • Updated 20 days ago • 2.96k • 243

louisbrulenaudet/tsdae-lemone-mbert-base

liked a space 24 days ago

Running

📖

LegalKit Retrieval

A binary Search with Scalar Rescoring through legal codes

liked a model 24 days ago

urchade/gliner_multi-v2.1

Token Classification • Updated 24 days ago • 14.6k • 37

liked a model 25 days ago

google/recurrentgemma-2b

Text Generation • Updated 11 days ago • 8.31k • 83

liked a dataset about 1 month ago

sentence-transformers/embedding-training-data

Updated Oct 17, 2021 • 12 • 86

liked 3 models about 1 month ago

NghiemAbe/PhoBert-base-GIST

databricks/dbrx-instruct

Text Generation • Updated 15 days ago • 78.1k • 1.05k

OrdalieTech/Solon-embeddings-large-0.1

Feature Extraction • Updated Mar 26 • 18k • 36

liked a dataset about 1 month ago

monsoon-nlp/greenbeing-proteins

Viewer • Updated Mar 30 • 36 • 2

liked 2 models about 1 month ago

ai21labs/Jamba-v0.1

Text Generation • Updated Apr 1 • 26.1k • 1.1k

monsoon-nlp/protein-matryoshka-embeddings

liked a dataset about 1 month ago

Cohere/BinaryVectorDB

Updated Mar 26 • 7

liked a model about 1 month ago

eek/span-marker-muppet-roberta-large-fewnerd-fine-super

Token Classification • Updated Mar 22 • 4 • 1

liked a dataset about 1 month ago

mixedbread-ai/wikipedia-embed-en-2023-11

Viewer • Updated Mar 22 • 29 • 7

liked a space about 1 month ago

Running

🔍

Quantized Retrieval

Efficient quantized retrieval over Wikipedia

liked a dataset about 2 months ago

Cohere/wikipedia-2023-11-embed-multilingual-v3-int8-binary

Viewer • Updated Mar 21 • 342 • 40

liked 2 models about 2 months ago

mixedbread-ai/mxbai-colbert-large-v1

Updated Apr 3 • 16.2k • 36

urchade/gliner_medium-v2.1

Token Classification • Updated 24 days ago • 4.38k • 8

liked a space about 2 months ago

Running

💻

GLiNER-Multiv2.1

liked a dataset about 2 months ago

Cohere/wikipedia-2023-11-embed-multilingual-v3

Viewer • Updated Mar 19 • 2.63k • 166

liked a model about 2 months ago

BEE-spoke-data/bert-plus-L8-v1.0-syntheticSTS-4k

liked a space about 2 months ago

Running

🌍

Major TOM Viewer

Quick View of Samples in the MajorTOM-Core Dataset

liked 3 models about 2 months ago

DeepMount00/universal_ner_ita

Token Classification • Updated 13 days ago • 3.39k • 21

urchade/gliner_medium-v2

Updated 24 days ago • 1.08k • 5

urchade/gliner_small-v2

Updated 24 days ago • 453 • 5

liked a space about 2 months ago

Running

💻

GLiNER-Multi, zero-shot NER

liked a model about 2 months ago

CohereForAI/c4ai-command-r-v01

Text Generation • Updated 24 days ago • 54.1k • 984

liked 2 spaces about 2 months ago

Running

🏢

Universal Ner ITA

Runtime error

126

💻

GLiNER-medium-v2.1, zero-shot NER

liked 4 models about 2 months ago

urchade/gliner_large-v2

Token Classification • Updated 24 days ago • 18.9k • 35

aspire/acge_text_embedding

mixedbread-ai/mxbai-embed-large-v1

Feature Extraction • Updated 16 days ago • 1.55M • 297

urchade/gliner_base

Token Classification • Updated 24 days ago • 20k • 57

Tom Aarsen

AI & ML interests

Articles

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

Snowflake Arctic St Demo

Ratchet + Phi

LegalKit Retrieval

Quantized Retrieval

GLiNER-Multiv2.1

Major TOM Viewer

GLiNER-Multi, zero-shot NER

Universal Ner ITA

GLiNER-medium-v2.1, zero-shot NER