crowsonkb / esgd
ESGD-M is a stochastic non-convex second order optimizer, suitable for training deep learning models, for PyTorch.
☆56Updated 2 years ago
Alternatives and similar repositories for esgd:
Users that are interested in esgd are comparing it to the libraries listed below
- CLOOB training (JAX) and inference (JAX and PyTorch)☆70Updated 2 years ago
- Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch☆89Updated 3 years ago
- A GPT, made only of MLPs, in Jax☆57Updated 3 years ago
- Contrastive Language-Image Pretraining☆142Updated 2 years ago
- Refactoring dalle-pytorch and taming-transformers for TPU VM☆60Updated 3 years ago
- Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.☆60Updated 2 years ago
- Unified API to facilitate usage of pre-trained "perceptor" models, a la CLIP☆39Updated 2 years ago
- ☆22Updated 2 years ago
- Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'☆38Updated 3 years ago
- Another attempt at a long-context / efficient transformer by me☆37Updated 2 years ago
- ☆28Updated 3 years ago
- Finetune the 1.4B latent diffusion text2img-large checkpoint from CompVis using deepspeed. (work-in-progress)☆36Updated 2 years ago
- A CLIP conditioned Decision Transformer.☆22Updated 3 years ago
- Pedagogical codebase for a simplified score-based generative model design, with training loop☆39Updated 3 years ago
- Script and models for clustering LAION-400m CLIP embeddings.☆25Updated 3 years ago
- CLOOB Conditioned Latent Diffusion training and inference code☆112Updated 2 years ago
- ☆64Updated 3 years ago
- ☆21Updated last year
- ☆13Updated 3 years ago
- ☆27Updated 3 years ago
- checkpoints for glide finetuned on laion and other datasets. wip.☆50Updated 2 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆48Updated 3 years ago
- An open source implementation of CLIP.☆32Updated 2 years ago
- A JAX nn library☆21Updated 11 months ago
- ☆86Updated 2 years ago
- Describe the format of image/text datasets☆11Updated 2 years ago
- A new play-and-plug method of controlling an existing generative model with conditioning attributes and their compositions.☆71Updated 3 years ago
- JAX implementation ViT-VQGAN☆80Updated 2 years ago
- GLIDE: a diffusion-based text-conditional image synthesis model☆20Updated 3 years ago
- Texture mapping with variational auto-encoders☆40Updated 3 years ago