Data loaders and abstractions for text and NLP
A natural language interface for computers
Stanford NLP Python library for many human languages
Underthesea - Vietnamese NLP Toolkit
Superlinked is a Python framework for AI Engineers
Industrial-strength Natural Language Processing (NLP)
The Classical Language Toolkit
ExtractThinker is a Document Intelligence library for LLMs
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
ReFT: Representation Finetuning for Language Models
A Repo For Document AI
Trained models & code to predict toxic comments
Extract schema, statistics and entities from datasets
A Heterogeneous Benchmark for Information Retrieval
The most accurate natural language detection library for Python
Persian NLP Toolkit
WikiChat is an improved RAG
Pretrained model hub for Keras 3
Toolkit for conversational AI
Easy-to-use and high-performance NLP and LLM framework
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models
Fast and customizable framework for automatic ML model creation
The no-nonsense RAG chunking library
The library to build & auto-optimize LLM applications
Han Language Processing