AdaptiveAttention

A generative speech model for daily dialogue.

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

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.

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Setup and customize deep learning environment in seconds.

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

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

Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.

Probabilistic time series modeling in Python

Deep Learning GPU Training System