Youngjoon Jang's picture

Youngjoon Jang

yjoonjang

·

yjoonjang

AI & ML interests

None yet

Recent Activity

reacted to tomaarsen's post with 🔥 about 8 hours ago

I just released Sentence Transformers v4.1; featuring ONNX and OpenVINO backends for rerankers offering 2-3x speedups and improved hard negatives mining which helps prepare stronger training datasets. Details: 🏎️ ONNX, OpenVINO, Optimization, Quantization - I've added ONNX and OpenVINO support with just one extra argument: "backend" when loading the CrossEncoder reranker, e.g.: `CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2", backend="onnx")` - The `export_optimized_onnx_model`, `export_dynamic_quantized_onnx_model`, and `export_static_quantized_openvino_model` functions now work with CrossEncoder rerankers, allowing you to optimize (e.g. fusions, gelu approximations, etc.) or quantize (int8 weights) rerankers. - I've uploaded ~340 ONNX & OpenVINO models for all existing models under the cross-encoder Hugging Face organization. You can use these without having to export when loading. ⛏ Improved Hard Negatives Mining - Added 'absolute_margin' and 'relative_margin' arguments to `mine_hard_negatives`. - `absolute_margin` ensures that `sim(query, negative) < sim(query, positive) - absolute_margin`, i.e. an absolute margin between the negative & positive similarities. - `relative_margin` ensures that `sim(query, negative) < sim(query, positive) * (1 - relative_margin)`, i.e. a relative margin between the negative & positive similarities. - Inspired by the excellent NV-Retriever paper from NVIDIA. And several other small improvements. Check out the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v4.1.0 With this release, I introduce near-feature parity between the SentenceTransformer embedding & CrossEncoder reranker models, which I've wanted to do for quite some time! With rerankers very strongly supported now, it's time to look forward to other useful architectures!

upvoted a paper about 8 hours ago

MIEB: Massive Image Embedding Benchmark

published a model 7 days ago

yjoonjang/preranker-v1

View all activity

Organizations

yjoonjang's activity

upvoted a paper about 8 hours ago

MIEB: Massive Image Embedding Benchmark

Paper • 2504.10471 • Published 1 day ago • 10

upvoted a collection 29 days ago

EXAONE-Deep

EXAONE reasoning model series of 2.4B, 7.8B, and 32B, optimized for reasoning tasks including math and coding • 9 items • Updated 29 days ago • 86

upvoted a collection 8 months ago

Magpie-Llama3.1 Datasets

Dataset built with Meta Llama 3.1 70B. • 6 items • Updated Jan 13 • 3