The Classical Language Toolkit
Dealing with all unstructured data, such as reverse image search
The most accurate natural language detection library for Python
An LLM-powered knowledge curation system that researches topics
Stanford NLP Python library for many human languages
Large Language Model Text Generation Inference
The no-nonsense RAG chunking library
Trained models & code to predict toxic comments
Underthesea - Vietnamese NLP Toolkit
Sparsity-aware deep learning inference runtime for CPUs
Toolkit for conversational AI
An easy-to-use LLMs quantization package with user-friendly apis
Superlinked is a Python framework for AI Engineers
Persian NLP Toolkit
WikiChat is an improved RAG
ReFT: Representation Finetuning for Language Models
A Repo For Document AI
Openai style api for open large language models
A natural language interface for computers
Industrial-strength Natural Language Processing (NLP)
Easy-to-use and high-performance NLP and LLM framework
Data loaders and abstractions for text and NLP
Data and tools for generating and inspecting OLMo pre-training data
Han Language Processing
Extract schema, statistics and entities from datasets