mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Post-training with Tinker

AI agents running research on single-GPU nanochat training automatically

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

Final project starter code for the question answering final project, for Natural Language Processing at UT Austin

YSDA course in Natural Language Processing

CoVoST: A Large-Scale Multilingual Speech-To-Text Translation Corpus (CC0 Licensed)

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Make huge neural nets fit in memory

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

A system for generating training labels via natural language explanations

Neural Text-Entity Encoder (NTEE)

YAGO is a large semantic knowledge base, derived from Wikipedia, WordNet, WikiData, GeoNames, and other data sources

PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

PyTorch implementation of the position-aware attention model for relation extraction

Code for neural-el - EMNLP'17

Facebook AI Research Sequence-to-Sequence Toolkit

Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

Numpy exercises.

FAst Lookups of Cosine and Other Nearest Neighbors (based on fast locality-sensitive hashing)

Oxford Deep NLP 2017 course

SLING - A natural language frame semantics parser

PyTorch Tutorial for Deep Learning Researchers

An open-source NLP research library, built on PyTorch.

Methods to get the probability of a changepoint in a time series.

Python wrapper for Stanford CoreNLP.

A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling