kim

skcandx
ยท

AI & ML interests

None yet

Recent Activity

replied to tomaarsen's post about 1 month ago
๐Ÿš€ Sentence Transformers v3.1 is out! Featuring a hard negatives mining utility to get better models out of your data, a new strong loss function, training with streaming datasets, custom modules, bug fixes, small additions and docs changes. Here's the details: โ› Hard Negatives Mining Utility: Hard negatives are texts that are rather similar to some anchor text (e.g. a question), but are not the correct match. They're difficult for a model to distinguish from the correct answer, often resulting in a stronger model after training. ๐Ÿ“‰ New loss function: This loss function works very well for symmetric tasks (e.g. clustering, classification, finding similar texts/paraphrases) and a bit less so for asymmetric tasks (e.g. question-answer retrieval). ๐Ÿ’พ Streaming datasets: You can now train with the datasets.IterableDataset, which doesn't require downloading the full dataset to disk before training. As simple as "streaming=True" in your "datasets.load_dataset". ๐Ÿงฉ Custom Modules: Model authors can now customize a lot more of the components that make up Sentence Transformer models, allowing for a lot more flexibility (e.g. multi-modal, model-specific quirks, etc.) โœจ New arguments to several methods: encode_multi_process gets a progress bar, push_to_hub can now be done to different branches, and CrossEncoders can be downloaded to specific cache directories. ๐Ÿ› Bug fixes: Too many to name here, check out the release notes! ๐Ÿ“ Documentation: A particular focus on clarifying the batch samplers in the Package Reference this release. Check out the full release notes here โญ: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.1.0 I'm very excited to hear your feedback, and I'm looking forward to the future changes that I have planned, such as ONNX inference! I'm also open to suggestions for new features: feel free to send me your ideas.
View all activity

Organizations

None yet

skcandx's activity

Be a person of basic courtesy.

#1 opened about 1 month ago by
skcandx