Knowledgator Engineering

Knowledgator Engineering

Open-source ML research organization
#63136205 followers0 following
1 point

About

We are focused on expanding human knowledge through fundamental models for information extraction. Focused on groundbreaking research, we develop ML solutions for information extraction that overcome the limitations of large-scale generative models, ensuring resource efficiency and task-specific precision. Our core is open-source, we believe in advancing AI through transparency and shared innovation, inviting you to join us in shaping technology for the common good.

Links

Hugging Face
Website
AI Playground

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Maker History

  • LiqFit
    LiqFitNew revolutionized way of NLP model fine-tuning
    Jan 2024
  • Zero-shot Named Entity Recognition
    Zero-shot Named Entity RecognitionIdentify and extract any custom key entities within the text
    Nov 2023
  • Comprehend-it
    Comprehend-itCategorize, analyze sentiment, or assign any tags to text
    Nov 2023
    • 🎉
    Joined Product HuntNovember 6th, 2023

Forums

Knowledgator Engineering•

2yr ago

Next-Generation Text Classification - Categorize, analyze sentiment, or assign any tags to text

Categorize, assign tags, or analyze the sentiment of any text, up to 150k tokens. Comprehend-it is a next-generation text classification model designed for zero-shot, multi-label categorization with output scoring. Test in our AI Playground, no registration.
Knowledgator Engineering•

2yr ago

Adaptive Named Entity Recognition (NER) - Identify and extract any custom key entities within the text

Identify a wide range of entities like company names and product features in any text with our NER model. Zero-shot learning, high accuracy, and cost-efficient processing up to 150k tokens. Try it in our AI Playground, no registration needed.
Knowledgator Engineering•

2yr ago

LiqFit - New revolutionized way of NLP model fine-tuning

LiqFit(Language Inference Quick Fit) - our new framework for few-shot learning of cross-encoder models. It's easy to use and incredibly effective for tasks like text classification, NER, and Q&A, achieving competitive results with just 8 examples per label!
View more