A natural language interface for computers
Stanford NLP Python library for many human languages
Han Language Processing
Bring the notion of Model-as-a-Service to life
Training data (data labeling, annotation, workflow) for all data types
A library for deep learning end-to-end dialog systems and chatbots
Toolkit for conversational AI
Build AI-powered semantic search applications
Trained models & code to predict toxic comments
Persian NLP Toolkit
WikiChat is an improved RAG
ReFT: Representation Finetuning for Language Models
Easy-to-use and high-performance NLP and LLM framework
ExtractThinker is a Document Intelligence library for LLMs
Superlinked is a Python framework for AI Engineers
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models
Fast and customizable framework for automatic ML model creation
Underthesea - Vietnamese NLP Toolkit
A Heterogeneous Benchmark for Information Retrieval
The no-nonsense RAG chunking library
The library to build & auto-optimize LLM applications
The Classical Language Toolkit
Data and tools for generating and inspecting OLMo pre-training data
Semantic search and workflows for medical/scientific papers
Efficient Retrieval Augmentation and Generation Framework