956 194 684

Tom Aarsen

tomaarsen

https://linkedin.com/in/tomaarsen

AI & ML interests

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

Recent Activity

liked a model about 6 hours ago

HuggingFaceTB/SmolVLM-256M-Instruct

new activity about 6 hours ago

sentence-transformers/all-MiniLM-L6-v2:Should I be concerned about "UserWarning: TypedStorage is deprecated. " when using the model with python 3.11?

posted an update about 7 hours ago

I just released Sentence Transformers v3.4.0, featuring a memory leak fix, compatibility between the powerful Cached... losses and the Matryoshka loss modifier, and a bunch of fixes & small features. 🪆 Matryoshka & Cached loss compatibility It is now possible to combine the powerful Cached... losses (which use in-batch negatives & a caching mechanism to allow for endless batch size & negatives) with the Matryoshka loss modifier which modifies a base loss such that it is trained not only on the maximum dimensionality (e.g. 1024 dimensions), but also on many lower dimensions (e.g. 768, 512, 256, 128, 64, 32). After training, these models' embeddings can be truncated for faster retrieval, etc. 🎞️ Resolve memory leak when Model and Trainer are reinitialized Due to a circular dependency between Trainer -> Model -> ModelCardData -> Trainer, deleting both the trainer & model still didn't free up the memory. This led to a memory leak in scripts where you repeatedly do so. ➕ New Features Many new small features, e.g. multi-GPU support for 'mine_hard_negatives', a 'margin' parameter to TripletEvaluator, and Matthews Correlation Coefficient in the BinaryClassificationEvaluator. 🐛 Bug Fixes Also a bunch of fixes, for example that subsequent batches were not sorted when using the "no_duplicates" batch sampler. See the release notes for more details. Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.4.0 Big thanks to all community members who assisted in this release. 10 folks with their first contribution this time around!

View all activity

Articles

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22, 2024

• 70

🪆 Introduction to Matryoshka Embedding Models

Feb 23, 2024

• 71

SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit

Dec 6, 2023

• 6

🕳️ Attention Sinks in LLMs for endless fluency

Oct 9, 2023

• 7

Organizations

tomaarsen's activity

liked a model about 6 hours ago

HuggingFaceTB/SmolVLM-256M-Instruct

Image-Text-to-Text • Updated about 10 hours ago • 244 • 29

New activity in sentence-transformers/all-MiniLM-L6-v2 about 6 hours ago

Should I be concerned about "UserWarning: TypedStorage is deprecated. " when using the model with python 3.11?

#97 opened about 7 hours ago by

poohlio

posted an update about 7 hours ago

Post

197

I just released Sentence Transformers v3.4.0, featuring a memory leak fix, compatibility between the powerful Cached... losses and the Matryoshka loss modifier, and a bunch of fixes & small features.

🪆 Matryoshka & Cached loss compatibility
It is now possible to combine the powerful Cached... losses (which use in-batch negatives & a caching mechanism to allow for endless batch size & negatives) with the Matryoshka loss modifier which modifies a base loss such that it is trained not only on the maximum dimensionality (e.g. 1024 dimensions), but also on many lower dimensions (e.g. 768, 512, 256, 128, 64, 32).
After training, these models' embeddings can be truncated for faster retrieval, etc.

🎞️ Resolve memory leak when Model and Trainer are reinitialized
Due to a circular dependency between Trainer -> Model -> ModelCardData -> Trainer, deleting both the trainer & model still didn't free up the memory.
This led to a memory leak in scripts where you repeatedly do so.

➕ New Features
Many new small features, e.g. multi-GPU support for 'mine_hard_negatives', a 'margin' parameter to TripletEvaluator, and Matthews Correlation Coefficient in the BinaryClassificationEvaluator.

🐛 Bug Fixes
Also a bunch of fixes, for example that subsequent batches were not sorted when using the "no_duplicates" batch sampler. See the release notes for more details.

Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.4.0

Big thanks to all community members who assisted in this release. 10 folks with their first contribution this time around!