facebookresearch / fairseqLinks
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
β31,750Updated 2 months ago
Alternatives and similar repositories for fairseq
Users that are interested in fairseq are comparing it to the libraries listed below
Sorting:
- π€ Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal modelβ¦β148,877Updated this week
- Unsupervised text tokenizer for Neural Network-based text generation.β11,199Updated last week
- Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.β30,045Updated this week
- Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"β6,415Updated 4 months ago
- An open-source NLP research library, built on PyTorch.β11,874Updated 2 years ago
- BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)β7,610Updated 3 months ago
- An annotated implementation of the Transformer paper.β6,479Updated last year
- Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.β16,433Updated 2 years ago
- Open Source Neural Machine Translation and (Large) Language Models in PyTorchβ6,932Updated 5 months ago
- State-of-the-Art Text Embeddingsβ17,437Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.β39,899Updated this week
- Trax β Deep Learning with Clear Code and Speedβ8,267Updated this week
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalitiesβ21,681Updated last month
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorchβ8,779Updated last week
- π€ PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.β19,447Updated this week
- A framework for training and evaluating AI models on a variety of openly available dialogue datasets.β10,612Updated last year
- A PyTorch implementation of the Transformer model in "Attention is All You Need".β9,361Updated last year
- Ongoing research training transformer models at scaleβ13,377Updated this week
- Google Researchβ36,250Updated last week
- Visualizer for neural network, deep learning and machine learning modelsβ31,295Updated this week
- Tensors and Dynamic neural networks in Python with strong GPU accelerationβ92,776Updated this week
- Google AI 2018 BERT pytorch implementationβ6,449Updated last year
- π₯ Fast State-of-the-Art Tokenizers optimized for Research and Productionβ10,033Updated this week
- A very simple framework for state-of-the-art Natural Language Processing (NLP)β14,275Updated 2 weeks ago
- A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) trainingβ22,521Updated last year
- Code and documentation to train Stanford's Alpaca models, and generate the data.β30,132Updated last year
- TensorFlow code and pre-trained models for BERTβ39,474Updated last year
- A library for efficient similarity search and clustering of dense vectors.β36,863Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.β43,960Updated 8 months ago
- π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (iβ¦β9,069Updated last week