Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

all kinds of text classification models and more with deep learning

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

A collection of important graph embedding, classification and representation learning papers with implementations.

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

A simple but complete full-attention transformer with a set of promising experimental features from various papers

A TensorFlow Implementation of the Transformer: Attention Is All You Need

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

Keras Attention Layer (Luong and Bahdanau scores).

Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning

My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!

Reformer, the efficient Transformer, in Pytorch

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released

基もと于金融きんゆう-司法しほう领域(兼有けんゆう闲聊性せい质)的てき聊天机つくえ器き人じん，其中的てき主要しゅよう模も块有信しん息いき抽取、NLU、NLG、知ち识图谱等，并且利用りようDjango整合せいごう了りょう前ぜん端はし展示てんじ,目前もくぜん已やめ经封装そう了りょうnlp和わkg的てきrestful接せっ口こう

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch