Liang

dreamhope

AI & ML interests

None yet

Recent Activity

updated a collection 1 day ago

LLM technique

liked a Space 5 days ago

HuggingFaceH4/blogpost-scaling-test-time-compute

liked a model 5 days ago

microsoft/bitnet-b1.58-2B-4T

View all activity

Organizations

dreamhope's activity

updated a collection 1 day ago

LLM technique

Collection

2 items • Updated 1 day ago

liked a Space 5 days ago

548

Scaling test-time compute

📈

Enhance math problem solving by scaling test-time compute

liked a model 5 days ago

microsoft/bitnet-b1.58-2B-4T

Text Generation • Updated 2 days ago • 13k • 638

reacted to tomaarsen's post with 🔥 5 days ago

Post

2523

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!