47 2 73

Yeb Havinga PRO

yhavinga

yhavinga

AI & ML interests

None yet

Recent Activity

reacted to tomaarsen's post with 😎 4 days 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!

updated a dataset 4 days ago

yhavinga/Openhermes-2.5-dutch-97k

liked a dataset 7 days ago

bespokelabs/Bespoke-Stratos-17k

View all activity

Organizations

yhavinga's activity

New activity in yhavinga/gpt-neo-1.3B-dutch 18 days ago

Adding `safetensors` variant of this model

#1 opened over 1 year ago by

SFconvertbot

New activity in yhavinga/squad_v2_dutch about 1 month ago

Translation model used?

#2 opened about 2 months ago by

saattrupdan

New activity in yhavinga/t5-v1.1-base-dutch-cased about 1 month ago

Adding `safetensors` variant of this model

#1 opened 3 months ago by

SFconvertbot

New activity in yhavinga/t5-base-dutch about 1 month ago

Adding `safetensors` variant of this model

#4 opened 3 months ago by

SFconvertbot

New activity in yhavinga/ul2-small-dutch about 1 month ago

Adding `safetensors` variant of this model

#1 opened about 2 months ago by

SFconvertbot

New activity in yhavinga/orpo-dpo-mix-dutch-40k 7 months ago

Librarian Bot: Add language metadata for dataset

#3 opened 7 months ago by

librarian-bot

Librarian Bot: Add dpo tag

#2 opened 7 months ago by

librarian-bot

New activity in yhavinga/t5-base-dutch 9 months ago

Topic refinmenet

#3 opened 9 months ago by

Harmpwns

New activity in yhavinga/ccmatrix 11 months ago

Update OPUS Download URL

#7 opened 11 months ago by

AkshitaS

New activity in yhavinga/t5-base-dutch about 1 year ago

classification in dutch text

#2 opened about 1 year ago by

Esmeray

New activity in flax-community/t5-base-cnn-dm over 1 year ago

Add evaluation results on the 3.0.0 config and test split of cnn_dailymail

#5 opened over 1 year ago by

autoevaluator

New activity in yhavinga/byt5-small-ccmatrix-en-nl over 1 year ago

Adding `safetensors` variant of this model

#2 opened over 1 year ago by

SFconvertbot

New activity in yhavinga/ul2-base-dutch over 1 year ago

UL2 Fine-tuned summarization model

#1 opened almost 2 years ago by

jumerckx

New activity in yhavinga/gpt-neo-125M-dutch almost 2 years ago

Adding `safetensors` variant of this model

#1 opened almost 2 years ago by

SFconvertbot

New activity in yhavinga/long-t5-tglobal-small-dutch-cnn-bf16-test almost 2 years ago

Adding `safetensors` variant of this model

#3 opened almost 2 years ago by

SFconvertbot

New activity in flax-community/t5-base-cnn-dm almost 2 years ago

Adding `safetensors` variant of this model

#4 opened almost 2 years ago by

SFconvertbot

New activity in yhavinga/gpt2-large-dutch almost 2 years ago

Adding `safetensors` variant of this model

#1 opened almost 2 years ago by

SFconvertbot

New activity in yhavinga/long-t5-tglobal-small-dutch-cnn almost 2 years ago

Adding `safetensors` variant of this model

#3 opened almost 2 years ago by

SFconvertbot

New activity in yhavinga/gpt2-medium-dutch almost 2 years ago

Adding `safetensors` variant of this model

#1 opened almost 2 years ago by

SFconvertbot

New activity in yhavinga/t5-v1.1-base-dutch-cnn-test almost 2 years ago

Adding `safetensors` variant of this model

#3 opened almost 2 years ago by

SFconvertbot