crowsonkb / esgdLinks
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
Sorting:
- ☆64Updated 3 years ago
- Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.☆60Updated 3 years ago
- CLOOB training (JAX) and inference (JAX and PyTorch)☆72Updated 3 years ago
- Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch☆89Updated 3 years ago
- Unified API to facilitate usage of pre-trained "perceptor" models, a la CLIP☆40Updated 2 years ago
- Refactoring dalle-pytorch and taming-transformers for TPU VM☆60Updated 3 years ago
- Script and models for clustering LAION-400m CLIP embeddings.☆26Updated 3 years ago
- ☆22Updated 3 years ago
- Finetune the 1.4B latent diffusion text2img-large checkpoint from CompVis using deepspeed. (work-in-progress)☆36Updated 3 years ago
- Contrastive Language-Image Pretraining☆144Updated 2 years ago
- ☆28Updated 3 years ago
- A GPT, made only of MLPs, in Jax☆58Updated 4 years ago
- CLOOB Conditioned Latent Diffusion training and inference code☆113Updated 3 years ago
- Pedagogical codebase for a simplified score-based generative model design, with training loop☆40Updated 3 years ago
- Another attempt at a long-context / efficient transformer by me☆38Updated 3 years ago
- GLIDE: a diffusion-based text-conditional image synthesis model☆20Updated 3 years ago
- ☆90Updated 2 years ago
- Google Colab notebooks☆43Updated 10 months ago
- Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'☆38Updated 3 years ago
- ☆27Updated 4 years ago
- High-Resolution Image Synthesis with Latent Diffusion Models☆61Updated 3 years ago
- Inverts CLIP text embeds to image embeds and visualizes with deep-image-prior.☆35Updated 3 years ago
- ☆14Updated 3 years ago
- ☆13Updated 4 years ago
- A CLIP conditioned Decision Transformer.☆22Updated 4 years ago
- ☆20Updated 3 years ago
- VQGAN+CLIP with some additional tuning. For notebooks and the command line.☆50Updated 3 years ago
- An open source implementation of CLIP.☆32Updated 2 years ago
- ☆33Updated 2 years ago
- ☆30Updated 3 years ago