Stepanov's picture

Open to Collab

Stepanov PRO

Ihor

·

https://knowledgator.com/

AI & ML interests

Text classification, computational biology, relations extraction, path reasoning

Recent Activity

liked a dataset about 13 hours ago

liked a model about 13 hours ago

OpenHands/openhands-critic-4b-v1.0

updated a model 1 day ago

knowledgator/gliner-relex-large-v0.5

View all activity

Organizations

upvoted a paper 17 days ago

The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder

Paper • 2602.18487 • Published 30 days ago • 5

upvoted a collection 23 days ago

Tiny Aya

Bridging Scale and Multilingual Depth • 10 items • Updated 24 days ago • 64

upvoted a collection 24 days ago

GLiClass-Instruct

Multi-task efficient zero-shot sequence classification models • 3 items • Updated 24 days ago • 5

upvoted a collection about 1 month ago

GLiNER- Linker

GLiNER-bi-Encoder models for entity linking with the GLiNKER framework • 3 items • Updated Feb 3 • 6

upvoted 2 articles 4 months ago

Article

Multi-Label Classification Model From Scratch: Step-by-Step Tutorial

Jan 8, 2024

•

50

Article

🛡️ Nemotron PII: Synthesized Data for Privacy-Preserving AI

Oct 28, 2025

•

34

upvoted a collection 6 months ago

GLiNER-PII

PII detection models developed in collaboration with Wordcab • 5 items • Updated Jan 29 • 22

upvoted a paper 6 months ago

LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

Paper • 2509.03405 • Published Sep 3, 2025 • 24

upvoted 2 collections 6 months ago

LMEnt

14 items • Updated Sep 14, 2025 • 6

mmBERT: a modern multilingual encoder

mmBERT is trained on 3T tokens from over 1800 languages, showing SoTA scores on benchmarks and exceptional low-resource performance • 16 items • Updated Sep 9, 2025 • 52

upvoted a paper 7 months ago

GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

Paper • 2508.07662 • Published Aug 11, 2025 • 9

upvoted 2 collections 8 months ago

GLiClass ONNX

GLiClass models converted to ONNX format, as well as 8bit quantization • 5 items • Updated Jul 29, 2025 • 4

GLiCLass-V3

Models for zero-shot text classification that are up to 50 times faster than Cross-Encoders and show the same or higher accuracy. • 8 items • Updated Jan 29 • 20

upvoted a collection 9 months ago

GLiNER-X

The Multilingual Named Entity Recognition (NER) model which is capable of identifying any entity type. • 6 items • Updated Jan 29 • 22

upvoted 2 articles 11 months ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26, 2025

•

185

Article

Announcing MamayLM, an efficient state-of-the-art Ukrainian LLM

Apr 23, 2025

•

63

upvoted a paper 11 months ago

GLiNER-biomed: A Suite of Efficient Models for Open Biomedical Named Entity Recognition

Paper • 2504.00676 • Published Apr 1, 2025 • 5

upvoted a collection 11 months ago

GLiNER-BioMed

Collection of high-quality GLiNER models tuned for working with biomedical data • 7 items • Updated Jan 29 • 7

upvoted an article about 1 year ago

Article

Introducing EuroBERT: A High-Performance Multilingual Encoder Model

Mar 10, 2025

•

147

upvoted a collection about 1 year ago

GLiNER-Biomed-1stg

12 items • Updated Feb 24, 2025 • 1