Data processing for and with foundation models
Industrial-strength Natural Language Processing (NLP)
Han Language Processing
A full spaCy pipeline and models for scientific/biomedical documents
Data and tools for generating and inspecting OLMo pre-training data
ExtractThinker is a Document Intelligence library for LLMs
A Repo For Document AI
The Classical Language Toolkit
An LLM-powered knowledge curation system that researches topics
Hub of ready-to-use datasets for ML models
Easy-to-use and high-performance NLP and LLM framework
Underthesea - Vietnamese NLP Toolkit
The no-nonsense RAG chunking library
Semantic search and workflows for medical/scientific papers
ReFT: Representation Finetuning for Language Models
A Heterogeneous Benchmark for Information Retrieval
Large Language Model Text Generation Inference
Efficient Retrieval Augmentation and Generation Framework
Sparsity-aware deep learning inference runtime for CPUs
Persian NLP Toolkit
Training data (data labeling, annotation, workflow) for all data types
Toolkit for conversational AI
The library to build & auto-optimize LLM applications
Neural Network Compression Framework for enhanced OpenVINO
Trained models & code to predict toxic comments