Hugging Face's logo
Tom Aarsen's picture
559 40 184

Tom Aarsen

tomaarsen
SeanLee97's profile picture LaferriereJC's profile picture flobraeuer's profile picture
·
https://linkedin.com/in/tomaarsen
tomaarsen
tomaarsen

AI & ML interests

NLP: text embeddings, named entity recognition, few-shot text classification

Articles

Organizations

Hugging Face's profile picture SetFit's profile picture Massive Text Embedding Benchmark's profile picture Hugging Face Fellows's profile picture Squadra Machine Learning Company's profile picture Hugging Face OSS Metrics's profile picture Open-Source AI Meetup's profile picture Sentence Transformers's profile picture Blog-explorers's profile picture Sentence Transformers Testing's profile picture Social Post Explorers's profile picture mLLM multilingual's profile picture

Posts 8

view post
Post
990
NuMind has just released 3 new state-of-the-art GLiNER models for Named Entity Recognition/Information Extraction. These GLiNER models allow you to specify any label that you want, and it'll find spans in the text corresponding to your label. It's been shown to work quite well on unusual domains, e.g. celestial entities in my picture.

There are 3 models released:
- numind/NuNER_Zero:
The primary model, SOTA & can detect really long entities.
- numind/NuNER_Zero-span:
Slightly better performance than NuNER Zero, but can't detect entities longer than 12 tokens.
- numind/NuNER_Zero-4k:
Slightly worse than NuNER Zero, but has a context length of 4k tokens.

Some more details about these models in general:
- They are *really* small, orders of magnitude smaller than LLMs, which don't reach this level of performance.
- Because they're small - they're fast: <1s per sentence on free GPUs.
- They have an MIT license: free commercial usage.

Try out the demo here: numind/NuZero
Or check out all of the models here: numind/nunerzero-zero-shot-ner-662b59803b9b438ff56e49e2

If there's ever a need for me to extract some information from any text: I'll be using these. Great work @Serega6678 !
view post
Post
2412
I've just stumbled upon some excellent work on (🇫🇷 French) retrieval models by @antoinelouis . Kudos to him!

- French Embedding Models: https://huggingface.co/collections/antoinelouis/dense-single-vector-bi-encoders-651523c0c75a3d4c44fc864d
- French Reranker Models: antoinelouis/cross-encoder-rerankers-651523f16efa656d1788a239
- French Multi-vector Models: https://huggingface.co/collections/antoinelouis/dense-multi-vector-bi-encoders-6589a8ee6b17c06872e9f075
- Multilingual Models: https://huggingface.co/collections/antoinelouis/modular-retrievers-65d53d0db64b1d644aea620c

A lot of these models use the MS MARCO Hard Negatives dataset, which I'm currently reformatting to be more easily usable. Notably, they should work out of the box without any pre-processing for training embedding models in the upcoming Sentence Transformers v3.
View all posts

Collections 9