deepvk/USER2-small
Sentence Similarity
ā¢
Updated
ā¢
948
ā¢
6
Tom Aarsen
tomaarsen
AI & ML interests
NLP: text embeddings, information retrieval, named entity recognition, few-shot text classification
Recent Activity
liked
a model
8 minutes ago
deepvk/USER2-small
liked
a model
9 minutes ago
deepvk/USER2-base
liked
a model
about 2 hours ago
vidore/colsmolvlm-v0.1
Organizations
tomaarsen's activity
liked
a
model
8 minutes ago
liked
a
model
9 minutes ago
liked
a
model
about 2 hours ago
liked
a
model
4 days ago
liked
2
models
5 days ago
reacted to
giadap's
post with š„
5 days ago
Post
1464
š¤ Just published: "Consent by Design" - exploring how we're building better consent mechanisms across the HF ecosystem!
Our research shows open AI development enables:
- Community-driven ethical standards
- Transparent accountability
- Context-specific implementations
- Privacy as core infrastructure
Check out our Space Privacy Analyzer tool that automatically generates privacy summaries of applications!
Effective consent isn't about perfect policies; it's about architectures that empower users while enabling innovation. š
Read more: https://huggingface.co/blog/giadap/consent-by-design
Our research shows open AI development enables:
- Community-driven ethical standards
- Transparent accountability
- Context-specific implementations
- Privacy as core infrastructure
Check out our Space Privacy Analyzer tool that automatically generates privacy summaries of applications!
Effective consent isn't about perfect policies; it's about architectures that empower users while enabling innovation. š
Read more: https://huggingface.co/blog/giadap/consent-by-design
Use the DistilBertTokenizer for this DistilBERT-based model
1
#6 opened 5 days ago
by
tomaarsen
Use the DistilBertTokenizer for this DistilBERT-based model
#4 opened 5 days ago
by
tomaarsen
upvoted
a
paper
7 days ago
posted
an
update
7 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:
šļø ONNX, OpenVINO, Optimization, Quantization
- I've added ONNX and OpenVINO support with just one extra argument: "backend" when loading the CrossEncoder reranker, e.g.:
- The
- 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.
ā Improved Hard Negatives Mining
- Added 'absolute_margin' and 'relative_margin' arguments to
-
-
- 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!
šļø 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.
ā 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!
liked
2
models
7 days ago
Push tokenizer again
9
#7 opened 14 days ago
by
tomaarsen
updated
3
models
7 days ago