Stanford NLP Python library for many human languages
A natural language interface for computers
The no-nonsense RAG chunking library
Extract schema, statistics and entities from datasets
ReFT: Representation Finetuning for Language Models
Efficient Retrieval Augmentation and Generation Framework
A full spaCy pipeline and models for scientific/biomedical documents
Trained models & code to predict toxic comments
Easy-to-use and high-performance NLP and LLM framework
A Heterogeneous Benchmark for Information Retrieval
The Classical Language Toolkit
Semantic search and workflows for medical/scientific papers
An LLM-powered knowledge curation system that researches topics
Data and tools for generating and inspecting OLMo pre-training data
Large Language Model Text Generation Inference
ExtractThinker is a Document Intelligence library for LLMs
Superlinked is a Python framework for AI Engineers
Pretrained model hub for Keras 3
Neural Network Compression Framework for enhanced OpenVINO
Efficient few-shot learning with Sentence Transformers
Industrial-strength Natural Language Processing (NLP)
WikiChat is an improved RAG
Underthesea - Vietnamese NLP Toolkit
Data processing for and with foundation models
Bring the notion of Model-as-a-Service to life