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

AI & ML interests

Text classification, relations extraction, NER, computational biology

Recent Activity
werent4  authored a paper 1 day ago
The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder
alexandrlukashov  authored a paper 1 day ago
The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder
Ihor  authored a paper 3 days ago
The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder
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
werent4 
authored a paper 1 day ago
alexandrlukashov 
authored a paper 1 day ago
Ihor 
authored a paper 3 days ago
BioMike 
authored a paper 3 days ago
Ihor 
updated 7 models 3 days ago
Ihor 
updated a Space 6 days ago
Ihor 
updated 3 models 7 days ago
Ihor 
posted an update 9 days ago
view post
Post
218

🧠 One Model to Classify, Verify, and Guard — Meet GLiClass-Instruct

When we first released GLiClass, it was a fast, zero-shot text classifier that could rival cross-encoders at a fraction of the cost. But classification alone wasn't enough. Our real ambition was a single, lightweight model that could handle the diverse range of text-understanding tasks via classification.
We are excited to announce GLiClass-Instruct – a leap forward that transforms GLiClass from a classifier into an instruction-following, multi-task engine.
What's new:
▪️ Hierarchical labeling: organize labels into structured groups for complex taxonomies
▪️ In-context learning via examples: provide few-shot examples to adapt on the fly, no fine-tuning needed
▪️ Prompting support: guide classification behavior with natural-language task descriptions
▪️ EWC for preventing catastrophic forgetting: add new capabilities without losing old ones
▪️ 3x faster inference thanks to FlashDeBERTa
New multi-task capabilities:
Beyond topic classification and sentiment analysis, GLiClass now supports:
▪️ Hallucination detection: verify whether LLM outputs are grounded in context
▪️ Rule-following verification: check if content complies with custom guidelines
▪️ Safety classification: detect prompt injections, jailbreaks, and harmful requests
These tasks are crucial for building reliable and efficient agentic systems, where every LLM output needs to be verified, every user input needs to be screened, and every response needs to follow the rules, all at minimal latency.
We release 3 instruction-following models (edge, base, large), with the large model matching SoTA classification models while unlocking entirely new task categories.
🔗 Explore more:
GitHub repo: https://github.com/Knowledgator/GLiClass
Models: https://huggingface.co/knowledgator/gliclass-multitask-large-v1.0
Our other solutions: https://www.knowledgator.com/
alexandrlukashov 
updated a Space 10 days ago
Ihor 
published 2 models 10 days ago
Ihor 
updated a collection 10 days ago