🏗️ Building on HF

Tom Aarsen

tomaarsen

2308 720 2110

pkedzia's profile picture

Sunaked's profile picture

dnth's profile picture

https://linkedin.com/in/tomaarsen

tomaarsen
tomaarsen
tomaarsen
tomaarsen.com

AI & ML interests

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

Recent Activity

liked a model 1 day ago

VAGOsolutions/SauerkrautLM-MoEdernColBERT-115M

liked a model 1 day ago

VAGOsolutions/SauerkrautLM-MoEdernColBERT-27M

liked a model 1 day ago

VAGOsolutions/SauerkrautLM-MoEdernColBERT-1.5M

View all activity

Organizations

tomaarsen 's collections 16

Encoder comparison after equivalent retrieval fine-tuning

ModernBERT, Ettin and UltraBERT: 54 retrieval models, frozen data and results. Validation-selected models first. Matched training, one seed.

tomaarsen/encoder-comparison-20261014

38.2 MB
tomaarsen/encoder-comparison-20261014

Updated 12 days ago • 6.17k
tomaarsen/modernbert-base-dense-msmarco32k-1e-4-20261014

Sentence Similarity • 0.1B • Updated 12 days ago • 35
tomaarsen/modernbert-base-multivector-msmarco32k-3e-4-20261014

Feature Extraction • 0.1B • Updated 12 days ago • 33

Reranker Models for GooAQ

https://huggingface.co/blog/train-reranker

tomaarsen/reranker-ModernBERT-large-gooaq-bce

Text Ranking • 0.4B • Updated May 17, 2025 • 1.65k • • 9
tomaarsen/reranker-NeoBERT-gooaq-bce

Text Ranking • 0.2B • Updated Mar 25, 2025 • 15 • 2
tomaarsen/reranker-ModernBERT-base-gooaq-bce

Text Ranking • 0.1B • Updated Mar 25, 2025 • 136 • 3
tomaarsen/reranker-MiniLM-L12-gooaq-bce

Text Ranking • 33.4M • Updated Mar 25, 2025 • 37 • 1

Matryoshka Embedding Models

https://huggingface.co/blog/matryoshka

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

Sentence Similarity • 88.1M • Updated Dec 29, 2025 • 107 • 5
aspire/acge_text_embedding

Sentence Similarity • 0.3B • Updated Oct 23, 2024 • 457 • 150
dunzhang/stella-mrl-large-zh-v3.5-1792d

Sentence Similarity • 0.3B • Updated Nov 6, 2024 • 566 • 50
NeuML/pubmedbert-base-embeddings-matryoshka

Sentence Similarity • 0.1B • Updated Jun 26, 2025 • 1.91k • • 23

State-of-the-Art NER models - General purpose

tomaarsen/span-marker-bert-base-fewnerd-fine-super

Token Classification • 0.1B • Updated Sep 26, 2023 • 3.39k • 15
tomaarsen/span-marker-roberta-large-fewnerd-fine-super

Token Classification • 0.4B • Updated Mar 22, 2024 • 67 • 14
tomaarsen/span-marker-mbert-base-multinerd

Token Classification • 0.2B • Updated Sep 12, 2023 • 12.4k • 72
tomaarsen/span-marker-roberta-large-ontonotes5

Token Classification • 0.4B • Updated Sep 22, 2023 • 68 • 15

State-of-the-Art NER models - Acronyms

tomaarsen/span-marker-bert-base-uncased-acronyms

Token Classification • 0.1B • Updated Sep 27, 2023 • 16.8k • 6
tomaarsen/span-marker-bert-base-acronyms

Token Classification • 0.1B • Updated Sep 27, 2023 • 39 • 7

State-of-the-Art NER models - Tagalog

tomaarsen/span-marker-mbert-base-tlunified

Token Classification • 0.2B • Updated May 7, 2025 • 24 • 1
tomaarsen/span-marker-roberta-tagalog-base-tlunified

Token Classification • Updated Nov 17, 2023 • 26 • 1

SpanMarker NER Models

SpanMarker NER models for various domains

State-of-the-Art NER models - General purpose

Collection

5 items • Updated Jun 1 • 5
State-of-the-Art NER models - Biomedical domain

Collection

3 items • Updated Jun 1
State-of-the-Art NER models - Acronyms

Collection

2 items • Updated Jun 1
State-of-the-Art NER models - Keyphrases

Collection

1 item • Updated Jun 1 • 1

SetFit models

tomaarsen/setfit-all-MiniLM-L6-v2-sst2-32-shot

Text Classification • Updated Dec 4, 2023 • 42 • 7
tomaarsen/setfit-paraphrase-mpnet-base-v2-sst2-8-shot

Text Classification • Updated Nov 29, 2023 • 20 • 4

Qwen3 Rerankers converted to Sequence Classification

tomaarsen/Qwen3-Reranker-0.6B-seq-cls

Text Ranking • 0.6B • Updated Jul 10, 2025 • 119k • 39
tomaarsen/Qwen3-Reranker-4B-seq-cls

Text Ranking • 4B • Updated Jun 16, 2025 • 1.66k • 11
tomaarsen/Qwen3-Reranker-8B-seq-cls

Text Ranking • 8B • Updated Jun 16, 2025 • 423 • 11

Training with Prompts

See the Training with Prompts documentation for more details: https://sbert.net/examples/training/prompts/README.html

tomaarsen/mpnet-base-nq

Sentence Similarity • 0.1B • Updated Nov 7, 2024 • 104
tomaarsen/mpnet-base-nq-prompts

Sentence Similarity • 0.1B • Updated Nov 7, 2024 • 102 • 1
tomaarsen/bert-base-nq

Sentence Similarity • 0.1B • Updated Nov 7, 2024 • 110
tomaarsen/bert-base-nq-prompts

Sentence Similarity • 0.1B • Updated Nov 7, 2024 • 119

Reranker Models for MS MARCO

tomaarsen/reranker-msmarco-ModernBERT-base-lambdaloss

Text Ranking • 0.1B • Updated Mar 25, 2025 • 19 • 5
tomaarsen/reranker-msmarco-MiniLM-L12-H384-uncased-lambdaloss

Text Ranking • 33.4M • Updated Mar 25, 2025 • 14 • 3

State-of-the-Art NER models - Biomedical domain

tomaarsen/span-marker-bert-base-ncbi-disease

Token Classification • 0.1B • Updated Aug 9, 2023 • 26 • 6
tomaarsen/span-marker-bert-base-uncased-bionlp

Token Classification • 0.1B • Updated May 10, 2025 • 36 • 5
tomaarsen/span-marker-bert-base-uncased-sourcedata

Token Classification • Updated Sep 26, 2023 • 28 • 4

State-of-the-Art NER models - Keyphrases

tomaarsen/span-marker-bert-base-uncased-keyphrase-inspec

Token Classification • Updated Sep 26, 2023 • 11 • 12

State-of-the-Art NER models - Organizations

nbroad/span-marker-roberta-large-orgs-v1

Token Classification • 0.4B • Updated Nov 25, 2023 • 16 • 2
tomaarsen/span-marker-bert-base-orgs

Token Classification • Updated Nov 22, 2023 • 70 • 1
nbroad/span-marker-xdistil-l12-h384-orgs-v3

Token Classification • 33.4M • Updated Nov 25, 2023 • 12
tomaarsen/span-marker-bert-small-orgs

Token Classification • Updated Nov 22, 2023 • 12

Strong & Small Rerankers

Trained on MS MARCO using the a similar strategy as https://huggingface.co/cross-encoder/ms-marco-MiniLM-L12-v2, except with the Ettin base models

tomaarsen/ms-marco-ettin-150m-reranker

Text Ranking • 0.1B • Updated Nov 24, 2025 • 46 • 1
tomaarsen/ms-marco-ettin-68m-reranker

Text Ranking • 68.4M • Updated Nov 24, 2025 • 569
tomaarsen/ms-marco-ettin-32m-reranker

Text Ranking • 32M • Updated Nov 24, 2025 • 79
tomaarsen/ms-marco-ettin-17m-reranker

Text Ranking • 16.9M • Updated Nov 24, 2025 • 333

SetFitABSA models

tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-aspect

Text Classification • Updated Dec 6, 2023 • 4.35k • 4
tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-polarity

Text Classification • Updated Dec 6, 2023 • 4.22k
tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-aspect

Text Classification • 0.1B • Updated Apr 23, 2024 • 38 • 1
tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-polarity

Text Classification • 0.1B • Updated Apr 23, 2024 • 37

Encoder comparison after equivalent retrieval fine-tuning

ModernBERT, Ettin and UltraBERT: 54 retrieval models, frozen data and results. Validation-selected models first. Matched training, one seed.

tomaarsen/encoder-comparison-20261014

38.2 MB
tomaarsen/encoder-comparison-20261014

Updated 12 days ago • 6.17k
tomaarsen/modernbert-base-dense-msmarco32k-1e-4-20261014

Sentence Similarity • 0.1B • Updated 12 days ago • 35
tomaarsen/modernbert-base-multivector-msmarco32k-3e-4-20261014

Feature Extraction • 0.1B • Updated 12 days ago • 33

Qwen3 Rerankers converted to Sequence Classification

tomaarsen/Qwen3-Reranker-0.6B-seq-cls

Text Ranking • 0.6B • Updated Jul 10, 2025 • 119k • 39
tomaarsen/Qwen3-Reranker-4B-seq-cls

Text Ranking • 4B • Updated Jun 16, 2025 • 1.66k • 11
tomaarsen/Qwen3-Reranker-8B-seq-cls

Text Ranking • 8B • Updated Jun 16, 2025 • 423 • 11

Reranker Models for GooAQ

https://huggingface.co/blog/train-reranker

tomaarsen/reranker-ModernBERT-large-gooaq-bce

Text Ranking • 0.4B • Updated May 17, 2025 • 1.65k • • 9
tomaarsen/reranker-NeoBERT-gooaq-bce

Text Ranking • 0.2B • Updated Mar 25, 2025 • 15 • 2
tomaarsen/reranker-ModernBERT-base-gooaq-bce

Text Ranking • 0.1B • Updated Mar 25, 2025 • 136 • 3
tomaarsen/reranker-MiniLM-L12-gooaq-bce

Text Ranking • 33.4M • Updated Mar 25, 2025 • 37 • 1

Training with Prompts

See the Training with Prompts documentation for more details: https://sbert.net/examples/training/prompts/README.html

tomaarsen/mpnet-base-nq

Sentence Similarity • 0.1B • Updated Nov 7, 2024 • 104
tomaarsen/mpnet-base-nq-prompts

Sentence Similarity • 0.1B • Updated Nov 7, 2024 • 102 • 1
tomaarsen/bert-base-nq

Sentence Similarity • 0.1B • Updated Nov 7, 2024 • 110
tomaarsen/bert-base-nq-prompts

Sentence Similarity • 0.1B • Updated Nov 7, 2024 • 119

Matryoshka Embedding Models

https://huggingface.co/blog/matryoshka

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

Sentence Similarity • 88.1M • Updated Dec 29, 2025 • 107 • 5
aspire/acge_text_embedding

Sentence Similarity • 0.3B • Updated Oct 23, 2024 • 457 • 150
dunzhang/stella-mrl-large-zh-v3.5-1792d

Sentence Similarity • 0.3B • Updated Nov 6, 2024 • 566 • 50
NeuML/pubmedbert-base-embeddings-matryoshka

Sentence Similarity • 0.1B • Updated Jun 26, 2025 • 1.91k • • 23

Reranker Models for MS MARCO

tomaarsen/reranker-msmarco-ModernBERT-base-lambdaloss

Text Ranking • 0.1B • Updated Mar 25, 2025 • 19 • 5
tomaarsen/reranker-msmarco-MiniLM-L12-H384-uncased-lambdaloss

Text Ranking • 33.4M • Updated Mar 25, 2025 • 14 • 3

State-of-the-Art NER models - General purpose

tomaarsen/span-marker-bert-base-fewnerd-fine-super

Token Classification • 0.1B • Updated Sep 26, 2023 • 3.39k • 15
tomaarsen/span-marker-roberta-large-fewnerd-fine-super

Token Classification • 0.4B • Updated Mar 22, 2024 • 67 • 14
tomaarsen/span-marker-mbert-base-multinerd

Token Classification • 0.2B • Updated Sep 12, 2023 • 12.4k • 72
tomaarsen/span-marker-roberta-large-ontonotes5

Token Classification • 0.4B • Updated Sep 22, 2023 • 68 • 15

State-of-the-Art NER models - Biomedical domain

tomaarsen/span-marker-bert-base-ncbi-disease

Token Classification • 0.1B • Updated Aug 9, 2023 • 26 • 6
tomaarsen/span-marker-bert-base-uncased-bionlp

Token Classification • 0.1B • Updated May 10, 2025 • 36 • 5
tomaarsen/span-marker-bert-base-uncased-sourcedata

Token Classification • Updated Sep 26, 2023 • 28 • 4

State-of-the-Art NER models - Acronyms

tomaarsen/span-marker-bert-base-uncased-acronyms

Token Classification • 0.1B • Updated Sep 27, 2023 • 16.8k • 6
tomaarsen/span-marker-bert-base-acronyms

Token Classification • 0.1B • Updated Sep 27, 2023 • 39 • 7

State-of-the-Art NER models - Keyphrases

tomaarsen/span-marker-bert-base-uncased-keyphrase-inspec

Token Classification • Updated Sep 26, 2023 • 11 • 12

State-of-the-Art NER models - Tagalog

tomaarsen/span-marker-mbert-base-tlunified

Token Classification • 0.2B • Updated May 7, 2025 • 24 • 1
tomaarsen/span-marker-roberta-tagalog-base-tlunified

Token Classification • Updated Nov 17, 2023 • 26 • 1

State-of-the-Art NER models - Organizations

nbroad/span-marker-roberta-large-orgs-v1

Token Classification • 0.4B • Updated Nov 25, 2023 • 16 • 2
tomaarsen/span-marker-bert-base-orgs

Token Classification • Updated Nov 22, 2023 • 70 • 1
nbroad/span-marker-xdistil-l12-h384-orgs-v3

Token Classification • 33.4M • Updated Nov 25, 2023 • 12
tomaarsen/span-marker-bert-small-orgs

Token Classification • Updated Nov 22, 2023 • 12

SpanMarker NER Models

SpanMarker NER models for various domains

State-of-the-Art NER models - General purpose

Collection

5 items • Updated Jun 1 • 5
State-of-the-Art NER models - Biomedical domain

Collection

3 items • Updated Jun 1
State-of-the-Art NER models - Acronyms

Collection

2 items • Updated Jun 1
State-of-the-Art NER models - Keyphrases

Collection

1 item • Updated Jun 1 • 1

Strong & Small Rerankers

Trained on MS MARCO using the a similar strategy as https://huggingface.co/cross-encoder/ms-marco-MiniLM-L12-v2, except with the Ettin base models

tomaarsen/ms-marco-ettin-150m-reranker

Text Ranking • 0.1B • Updated Nov 24, 2025 • 46 • 1
tomaarsen/ms-marco-ettin-68m-reranker

Text Ranking • 68.4M • Updated Nov 24, 2025 • 569
tomaarsen/ms-marco-ettin-32m-reranker

Text Ranking • 32M • Updated Nov 24, 2025 • 79
tomaarsen/ms-marco-ettin-17m-reranker

Text Ranking • 16.9M • Updated Nov 24, 2025 • 333

SetFit models

tomaarsen/setfit-all-MiniLM-L6-v2-sst2-32-shot

Text Classification • Updated Dec 4, 2023 • 42 • 7
tomaarsen/setfit-paraphrase-mpnet-base-v2-sst2-8-shot

Text Classification • Updated Nov 29, 2023 • 20 • 4

SetFitABSA models

tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-aspect

Text Classification • Updated Dec 6, 2023 • 4.35k • 4
tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-polarity

Text Classification • Updated Dec 6, 2023 • 4.22k
tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-aspect

Text Classification • 0.1B • Updated Apr 23, 2024 • 38 • 1
tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-polarity

Text Classification • 0.1B • Updated Apr 23, 2024 • 37

Tom Aarsen

AI & ML interests

Recent Activity

Organizations

tomaarsen 's collections 16

tomaarsen/encoder-comparison-20261014

tomaarsen/encoder-comparison-20261014