583 57 211

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

about 24 hours ago

• 30

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Apr 3

• 6

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 37

Organizations

tomaarsen's activity

New activity in sentence-transformers/all-mpnet-base-v2 about 10 hours ago

Error deploying model for inference on Azure

#26 opened about 11 hours ago by

josef-dee

New activity in intfloat/e5-mistral-7b-instruct 2 days ago

Simplify usage; integrate Sentence Transformers (+ LlamaIndex/LangChain, etc.)

#39 opened about 1 month ago by

tomaarsen

New activity in w601sxs/b1ade-embed-kd 4 days ago

Nice work!

#1 opened 4 days ago by

tomaarsen

New activity in mteb/leaderboard 5 days ago

New model and mteb leaderboard refresh request

#117 opened 5 days ago by

nada5

New activity in sentence-transformers/all-MiniLM-L6-v2 7 days ago

Can I fine-tuning the model?

#56 opened about 2 months ago by

cathelloya

How is it able to give similarity scores for Russian?

#28 opened 9 months ago by

drmeir

New activity in tomaarsen/xlm-roberta-base-multilingual-en-ar-fr-de-es-tr-it 7 days ago

Credits

#1 opened 16 days ago by

roberto-viviani

New activity in DeepMount00/GLiNER_ITA_SMALL 8 days ago

Set "gliner" as the library

#1 opened 8 days ago by

tomaarsen

New activity in DeepMount00/GLiNER_ITA_LARGE 8 days ago

Set "gliner" as the library

#1 opened 8 days ago by

tomaarsen

New activity in DeepMount00/GLiNER_ITA_BASE 8 days ago

Set "gliner" as the library

#2 opened 8 days ago by

tomaarsen

New activity in EmergentMethods/gliner_medium_news-v2.1 8 days ago

Add "gliner" tag

#1 opened 8 days ago by

tomaarsen

New activity in EmergentMethods/gliner_large_news-v2.1 8 days ago

Add "gliner" tag

#1 opened 8 days ago by

tomaarsen

New activity in EmergentMethods/gliner_small_news-v2.1 8 days ago

Add "gliner" tag

#1 opened 8 days ago by

tomaarsen

New activity in mteb/leaderboard 8 days ago

Adding w601sxs/b1ade-embed to the leaderboard

#114 opened 12 days ago by

w601sxs

New activity in andersonbcdefg/lm_instruction_pairs 8 days ago

Add 'sentence-transformers' tag for easier discoverability

#2 opened 8 days ago by

tomaarsen

New activity in andersonbcdefg/synthetic_nli_part2 8 days ago

Add 'sentence-transformers' tag for easier discoverability

#1 opened 8 days ago by

tomaarsen

New activity in andersonbcdefg/synthetic_nli 8 days ago

Add 'sentence-transformers' tag for easier discoverability

#1 opened 8 days ago by

tomaarsen

New activity in andersonbcdefg/synthetic_tuples_gpt35_turbo 8 days ago

Add 'sentence-transformers' tag for easier discoverability

#3 opened 8 days ago by

tomaarsen

New activity in wongctroman/hktv-fine-tuned-cloudy-large-zh-metaphor14 13 days ago

TypeError: Pooling.init() got an unexpected keyword argument 'pooling_mode_weightedmean_tokens'

#1 opened 2 months ago by

Anthony-Sun

New activity in Pristinenlp/alime-embedding-large-zh 13 days ago

Set `sentence-transformers` as the model library

#1 opened 13 days ago by

tomaarsen

New activity in TownsWu/PEG 13 days ago

Ablations with InfoNCE

#5 opened 13 days ago by

tomaarsen

New activity in multi-train/emb-zeroshot-train 13 days ago

Add `sentence-transformers` tags

#1 opened 13 days ago by

tomaarsen

New activity in mteb/leaderboard 14 days ago

Request a restart for new SOTA Chinese embedding models

#101 opened about 1 month ago by

Jinkin

New activity in sensenova/piccolo-large-zh-v2 14 days ago

Add 'sentence-transformers' tag

#2 opened 14 days ago by

tomaarsen

New activity in sentence-transformers/all-mpnet-base-v2 14 days ago

Translation Task

#25 opened 14 days ago by

NairaRahim

New activity in PhilipMay/stsb_multi_mt 14 days ago

Add 'sentence-transformers' tag for easier discoverability

#7 opened 14 days ago by

tomaarsen

New activity in mteb/leaderboard 14 days ago

add german mteb overview tab

#113 opened 15 days ago by

aari1995

New activity in sentence-transformers/all-MiniLM-L6-v2 14 days ago

Semantic similarity between two texts !

#63 opened 15 days ago by

Systeme

New activity in nirantk/triplets 17 days ago

Add 'sentence-transformers' tag for easier discoverability

#3 opened 17 days ago by

tomaarsen

New activity in dwzhu/e5-base-4k 19 days ago

Remove `sentence-transformers` tags

#1 opened 19 days ago by

tomaarsen

New activity in mteb/leaderboard 21 days ago

add_followir_tab

#102 opened about 1 month ago by

orionweller

New activity in mteb/leaderboard 22 days ago

Refactor code: Pull leaderboards and models configurations out of the app.py

#106 opened 27 days ago by

eduagarcia

New activity in social-post-explorers/README 24 days ago

Optimized embedding method in RAG

#37 opened 24 days ago by

Sushanta007

New activity in WhereIsAI/github-issue-similarity 26 days ago

Add 'sentence-transformers' tag for easier discoverability

#2 opened 26 days ago by

tomaarsen

New activity in flax-sentence-embeddings/stackexchange_title_best_voted_answer_jsonl 28 days ago

Add 'sentence-transformers' tag for easier discoverability

#2 opened 28 days ago by

tomaarsen

New activity in flax-sentence-embeddings/stackexchange_titlebody_best_and_down_voted_answer_jsonl 28 days ago

Add 'sentence-transformers' tag for easier discoverability

#3 opened 28 days ago by

tomaarsen

New activity in flax-sentence-embeddings/stackexchange_math_jsonl 28 days ago

Add 'sentence-transformers' tag for easier discoverability

#2 opened 28 days ago by

tomaarsen

New activity in flax-sentence-embeddings/stackexchange_titlebody_best_voted_answer_jsonl 28 days ago

Add 'sentence-transformers' tag for easier discoverability

#4 opened 28 days ago by

tomaarsen

New activity in NetherlandsForensicInstitute/altlex-translated-nl 29 days ago

Add 'sentence-transformers' tag for easier discoverability

#1 opened 29 days ago by

tomaarsen

New activity in NetherlandsForensicInstitute/quora-duplicates-translated-nl 29 days ago

Add 'sentence-transformers' tag for easier discoverability

#1 opened 29 days ago by

tomaarsen

New activity in NetherlandsForensicInstitute/sentence-compression-translated-nl 29 days ago

Add 'sentence-transformers' tag for easier discoverability

#1 opened 29 days ago by

tomaarsen

New activity in NetherlandsForensicInstitute/simplewiki-translated-nl 29 days ago

Add 'sentence-transformers' tag for easier discoverability

#1 opened 29 days ago by

tomaarsen

New activity in NetherlandsForensicInstitute/stackexchange-duplicate-questions-translated-nl 29 days ago

Add 'sentence-transformers' tag for easier discoverability

#1 opened 29 days ago by

tomaarsen

New activity in NetherlandsForensicInstitute/wiki-atomic-edits-translated-nl 29 days ago

Add 'sentence-transformers' tag for easier discoverability

#2 opened 29 days ago by

tomaarsen

New activity in NetherlandsForensicInstitute/s2orc-citation-pairs-translated-nl 29 days ago

Add 'sentence-transformers' tag for easier discoverability

#1 opened 29 days ago by

tomaarsen

New activity in NetherlandsForensicInstitute/allnli-translated-nl 29 days ago

Add 'sentence-transformers' tag for easier discoverability

#2 opened 29 days ago by

tomaarsen

New activity in mteb/leaderboard about 1 month ago

Which retrieval task is missing?

#103 opened about 1 month ago by

Mihaiii

New activity in Mihaiii/qa-assistant about 1 month ago

Add tags

#1 opened about 1 month ago by

tomaarsen

New activity in Snowflake/snowflake-arctic-instruct about 1 month ago

Add Arctic modeling/config/tokenization files

#3 opened about 1 month ago by

tomaarsen

New activity in nomic-ai/nomic-embed-text-v1.5 about 1 month ago

Nomic-ai-embedding fine tuning with SentenceTransformersFinetuneEngine

#18 opened about 1 month ago by

Miheer29

New activity in mteb/leaderboard about 1 month ago

update metadata for gte-v1.5 series models

#99 opened about 1 month ago by

zyznull

New activity in Snowflake/snowflake-arctic-base about 1 month ago

Add Arctic modeling/config/tokenization files

#1 opened about 1 month ago by

tomaarsen

New activity in tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-aspect about 1 month ago

Adding `safetensors` variant of this model

#1 opened about 1 month ago by

SFconvertbot

New activity in tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-polarity about 1 month ago

Adding `safetensors` variant of this model

#1 opened about 1 month ago by

SFconvertbot

commented a paper about 1 month ago

LongEmbed: Extending Embedding Models for Long Context Retrieval

Paper • 2404.12096 • Published Apr 18 • 2 •

New activity in sentence-transformers/all-MiniLM-L6-v2 about 1 month ago

1 validation error for HuggingFaceHub

#59 opened about 1 month ago by

Suraj-Patil

New activity in Snowflake/snowflake-arctic-embed-m-long about 1 month ago

Upload ONNX weights

#4 opened about 1 month ago by

Xenova

New activity in mteb/leaderboard about 1 month ago

New model doesn't appear after Refresh

#100 opened about 1 month ago by

Mihaiii

New activity in mteb/results about 1 month ago

update gte-Qwen1.5-7B-instruct results

#47 opened about 1 month ago by

zyznull

New activity in Alibaba-NLP/gte-Qwen1.5-7B-instruct about 1 month ago

Simplify usage; integrate Sentence Transformers (+ LlamaIndex/LangChain, etc.)

#5 opened about 1 month ago by

tomaarsen

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

Error deploying model for inference on Azure

Simplify usage; integrate Sentence Transformers (+ LlamaIndex/LangChain, etc.)

Nice work!

New model and mteb leaderboard refresh request

Can I fine-tuning the model?

How is it able to give similarity scores for Russian?

Credits

Set "gliner" as the library

Set "gliner" as the library

Set "gliner" as the library

Add "gliner" tag

Add "gliner" tag

Add "gliner" tag

Adding w601sxs/b1ade-embed to the leaderboard

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

TypeError: Pooling.__init__() got an unexpected keyword argument 'pooling_mode_weightedmean_tokens'

Set `sentence-transformers` as the model library

Ablations with InfoNCE

Add `sentence-transformers` tags

Request a restart for new SOTA Chinese embedding models

Add 'sentence-transformers' tag

Translation Task

Add 'sentence-transformers' tag for easier discoverability

add german mteb overview tab

Semantic similarity between two texts !

Add 'sentence-transformers' tag for easier discoverability

Remove `sentence-transformers` tags

add_followir_tab

Refactor code: Pull leaderboards and models configurations out of the app.py

Optimized embedding method in RAG

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Add 'sentence-transformers' tag for easier discoverability

Which retrieval task is missing?

Add tags

Add Arctic modeling/config/tokenization files

Nomic-ai-embedding fine tuning with SentenceTransformersFinetuneEngine

update metadata for gte-v1.5 series models

Add Arctic modeling/config/tokenization files

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

1 validation error for HuggingFaceHub

Upload ONNX weights

New model doesn't appear after Refresh

update gte-Qwen1.5-7B-instruct results

Simplify usage; integrate Sentence Transformers (+ LlamaIndex/LangChain, etc.)

TypeError: Pooling.init() got an unexpected keyword argument 'pooling_mode_weightedmean_tokens'