Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

Text classification, relations extraction, NER, computational biology

Recent Activity
alexandrlukashov  updated a model about 5 hours ago
knowledgator/retrico-lm-9b-sft-dev
Ihor  new activity 5 days ago
knowledgator/opir-multitask-multilang-v1.0:What is the actual max-model-len for this model?
alexandrlukashov  updated a model 6 days ago
knowledgator/retrico-lm-9b-merged
View all activity

Papers

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

GLiClass: Generalist Lightweight Model for Sequence Classification Tasks

View all Papers

knowledgator 's collections 23

Opir
Efficient Multi-Task Safety Classification Models
GLiNER-relex
Zero-shot joint NER and relation extraction models
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.
GLiNER-BioMed
Collection of high-quality GLiNER models tuned for working with biomedical data
LLM2Encoder
Collection of initial models and models that use converted decoders to encoders as backbones
Universal token classification
Collection of universal token classification (UTC) models capable in prompt-tuned manner to solve many information extraction tasks.
GLiNER
Knowledgator GLiNER models for information extraction
Chemical Converters
Collection of models for converting chemical formats between each other.
GLiNER-X
The Multilingual Named Entity Recognition (NER) model which is capable of identifying any entity type.
ModernGLiClass
GLiClass with ModernBERT backbone
GLiClass
Generalist and Light-weighted Models for Zero-shot Text Classification
Zero-shot text classification models
Collection of the best zero-shot text classification models. Fine-tune them with few examples using LiqFit - https://github.com/Knowledgator/LiqFit.
Opir
Efficient Multi-Task Safety Classification Models
GLiNER-relex
Zero-shot joint NER and relation extraction models
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.
GLiNER-X
The Multilingual Named Entity Recognition (NER) model which is capable of identifying any entity type.
GLiNER-BioMed
Collection of high-quality GLiNER models tuned for working with biomedical data
ModernGLiClass
GLiClass with ModernBERT backbone
LLM2Encoder
Collection of initial models and models that use converted decoders to encoders as backbones
GLiClass
Generalist and Light-weighted Models for Zero-shot Text Classification
Universal token classification
Collection of universal token classification (UTC) models capable in prompt-tuned manner to solve many information extraction tasks.
Zero-shot text classification models
Collection of the best zero-shot text classification models. Fine-tune them with few examples using LiqFit - https://github.com/Knowledgator/LiqFit.
GLiNER
Knowledgator GLiNER models for information extraction
Chemical Converters
Collection of models for converting chemical formats between each other.