-
Mistral AI
- San Fransisco, Bay Area
Stars
Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate
A framework for the evaluation of autoregressive code generation language models.
Building a quick conversation-based search demo with Lepton AI.
Task-based datasets, preprocessing, and evaluation for sequence models.
Original Implementation of Prompt Tuning from Lester, et al, 2021
Pytorch library for fast transformer implementations
Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.
State-of-the-Art Text Embeddings
Fast and customizable text tokenization library with BPE and SentencePiece support
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
A summary of must-read papers for Neural Question Generation (NQG)
midi processor library for PerformanceRNN & MusicTransformer published by "Google Magenta"
Music GPT-2 Implementation with Relative Positional Embedding
🏋️ Python / Modern C++ Solutions of All 3716 LeetCode Problems (Weekly Update)
Dataset for JSB Chorales at different temporal resolutions, with train, validation, test split from Boulanger-Lewandowski (2012).
torch-optimizer -- collection of optimizers for Pytorch
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
CUDA kernels for generalized matrix-multiplication in PyTorch
Code for the paper "Do Massively Pretrained Language Models Make Better Storytellers?"
Fast, general, and tested differentiable structured prediction in PyTorch
Ongoing research training transformer models at scale
Tools for downloading and analyzing summaries and evaluating summarization systems. https://summari.es/
MASS: Masked Sequence to Sequence Pre-training for Language Generation
XLNet: Generalized Autoregressive Pretraining for Language Understanding
An implementation of training for GPT2, supports TPUs
A mix of GAN implementations including progressive growing