betacord / PSI
☆10Updated 5 months ago
Alternatives and similar repositories for PSI
Users that are interested in PSI are comparing it to the libraries listed below
Sorting:
- Kick-off repository for starting with Kaggle!☆13Updated 5 months ago
- ☆27Updated 4 months ago
- Efficient optimizers☆193Updated this week
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆528Updated 10 months ago
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated last year
- Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"☆553Updated 10 months ago
- Focused on fast experimentation and simplicity☆72Updated 4 months ago
- When it comes to optimizers, it's always better to be safe than sorry☆223Updated last month
- Train VAE like a boss☆278Updated 6 months ago
- supporting pytorch FSDP for optimizers☆80Updated 5 months ago
- ☆44Updated 2 months ago
- Huggingface-compatible SDXL Unet implementation that is readily hackable☆422Updated last year
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆231Updated 6 months ago
- ☆302Updated 10 months ago
- For optimization algorithm research and development.☆513Updated this week
- The repository for the code of the UltraFastBERT paper☆517Updated last year
- Text to Image Latent Diffusion using a Transformer core☆183Updated 8 months ago
- WIP☆93Updated 9 months ago
- My take on Flow Matching☆55Updated 4 months ago
- Serbian LLM Eval.☆94Updated last year
- Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"☆424Updated 5 months ago
- UNet diffusion model in pure CUDA☆604Updated 10 months ago
- A repository for log-time feedforward networks☆222Updated last year
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆233Updated 2 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆275Updated 11 months ago
- Flow-matching algorithms in JAX☆90Updated 9 months ago
- Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models☆543Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 9 months ago
- Solve puzzles. Learn CUDA.☆64Updated last year
- ☆20Updated 7 months ago