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
Openai style api for open large language models
Sparsity-aware deep learning inference runtime for CPUs
A natural language interface for computers
Superlinked is a Python framework for AI Engineers
Trained models & code to predict toxic comments
Persian NLP Toolkit
ReFT: Representation Finetuning for Language Models
Underthesea - Vietnamese NLP Toolkit
Industrial-strength Natural Language Processing (NLP)
Easy-to-use and high-performance NLP and LLM framework
Large Language Model Text Generation Inference
Han Language Processing
An easy-to-use LLMs quantization package with user-friendly apis
WikiChat is an improved RAG
Data and tools for generating and inspecting OLMo pre-training data
The no-nonsense RAG chunking library
A Heterogeneous Benchmark for Information Retrieval
Extract schema, statistics and entities from datasets
A full spaCy pipeline and models for scientific/biomedical documents
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models