The Classical Language Toolkit
Dealing with all unstructured data, such as reverse image search
A natural language interface for computers
Large Language Model Text Generation Inference
An LLM-powered knowledge curation system that researches topics
Module for automatic summarization of text documents and HTML pages
The no-nonsense RAG chunking library
The most accurate natural language detection library for Python
Trained models & code to predict toxic comments
Sparsity-aware deep learning inference runtime for CPUs
ReFT: Representation Finetuning for Language Models
Easy-to-use and high-performance NLP and LLM framework
Industrial-strength Natural Language Processing (NLP)
Han Language Processing
Data and tools for generating and inspecting OLMo pre-training data
Stanford NLP Python library for many human languages
A Heterogeneous Benchmark for Information Retrieval
Underthesea - Vietnamese NLP Toolkit
Decrypt encryptions without knowing the key or cipher
ExtractThinker is a Document Intelligence library for LLMs
Efficient Retrieval Augmentation and Generation Framework
Superlinked is a Python framework for AI Engineers
Neural Network Compression Framework for enhanced OpenVINO
Persian NLP Toolkit
WikiChat is an improved RAG