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 Space 2 days ago

piimb/pii-masking-benchmark-leaderboard

updated a model 6 days ago

knowledgator/gliner-pii-large-v1.0

liked a model 12 days ago

rizvandwiki/gender-classification-2

View all activity

Organizations

upvoted a collection 13 days ago

GLiClass-Multilang

Multi-lingual zero-shot text classification models • 3 items • Updated 13 days ago • 6

upvoted a paper about 1 month ago

GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer

Paper • 2311.08526 • Published Nov 14, 2023 • 14

upvoted a paper 3 months ago

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

Paper • 2602.18487 • Published Feb 11 • 6

upvoted 3 collections 3 months ago

Tiny Aya

Bridging Scale and Multilingual Depth • 10 items • Updated Feb 17 • 69

GLiClass-Instruct

Multi-task efficient zero-shot sequence classification models • 3 items • Updated 13 days ago • 5

GLiNER- Linker

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

upvoted 2 articles 6 months ago

Article

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

Valerii-Knowledgator

•

Jan 8, 2024

• 51

Article

🛡️ Nemotron PII: Synthesized Data for Privacy-Preserving AI

nvidia

•

Oct 28, 2025

• 34

upvoted a collection 8 months ago

GLiNER-PII

PII detection models developed in collaboration with Wordcab • 5 items • Updated Jan 29 • 23

upvoted a paper 8 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 8 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 • 53

upvoted a paper 9 months ago

GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

Paper • 2508.07662 • Published Aug 11, 2025 • 9

upvoted 2 collections 10 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 11 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 about 1 year ago

Article

Training and Finetuning Reranker Models with Sentence Transformers

tomaarsen

•

Mar 26, 2025

• 193

Article

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

INSAIT-Institute

•

Apr 23, 2025

• 65

upvoted a paper about 1 year 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 about 1 year ago

GLiNER-BioMed

Collection of high-quality GLiNER models tuned for working with biomedical data • 7 items • Updated Jan 29 • 9