Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Repository Index
47,133 repositories indexed
1–8 of 8 · Most stars
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
A collection of important graph embedding, classification and representation learning papers with implementations.
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Code for PaperRobot: Incremental Draft Generation of Scientific Ideas
Hierarchical Attentive Recurrent Tracking
TensorFlow implementation of the paper "Hierarchical Attention Networks for Document Classification"
A Tensorfflow implementation of Attend, Infer, Repeat