Stepanov's picture

Stepanov PRO

Ihor

·

https://knowledgator.com/

AI & ML interests

Text classification, computational biology, relations extraction, path reasoning

Recent Activity

liked a model 5 days ago

knowledgator/gliclass-large-v1.0-lw

liked a model 9 days ago

ModernVBERT/modernvbert

liked a model 9 days ago

pyannote/speaker-diarization-community-1

View all activity

Organizations

upvoted a collection 25 days ago

GLiNER-PII

PII detection models developed in collaboration with Wordcab • 5 items • Updated 27 days ago • 21

upvoted a paper about 1 month ago

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

Paper • 2509.03405 • Published Sep 3 • 23

upvoted 2 collections about 1 month ago

LMEnt

14 items • Updated Sep 14 • 5

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 • 45

upvoted a paper 2 months ago

GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

Paper • 2508.07662 • Published Aug 11 • 9

upvoted 2 collections 3 months ago

GLiClass ONNX

GLiClass models converted to ONNX format, as well as 8bit quantization • 5 items • Updated Jul 29 • 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 Aug 13 • 17

upvoted a collection 4 months ago

GLiNER-X

The Multilingual Named Entity Recognition (NER) model which is capable of identifying any entity type. • 6 items • Updated Jun 24 • 21

upvoted 2 articles 6 months ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26

• 167

Article

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

By

and 2 others •

Apr 23

• 61

upvoted a paper 7 months ago

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

Paper • 2504.00676 • Published Apr 1 • 5

upvoted a collection 7 months ago

GLiNER-BioMed

Collection of high-quality GLiNER models tuned for working with biomedical data • 7 items • Updated Apr 2 • 7

upvoted an article 8 months ago

Article

Introducing EuroBERT: A High-Performance Multilingual Encoder Model

By

and 3 others •

Mar 10

• 146

upvoted a collection 8 months ago

GLiNER-Biomed-1stg

12 items • Updated Feb 24 • 1

upvoted 3 articles 9 months ago

Article

Open-R1: Update #1

By

and 7 others •

Feb 2

• 305

Article

Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial

By

•

Jan 31

• 51

Article

Train 400x faster Static Embedding Models with Sentence Transformers

Jan 15

• 216

upvoted 3 collections about 1 year ago

Domain-specific GLiNER

6 items • Updated Jun 17, 2024 • 7

GLiNER

Knowledgator GLiNER models for information extraction • 8 items • Updated Aug 19 • 12

Qwen2

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated Jul 21 • 370