Skip to content
Fossfits

transformers.

Listed 18Updated Sep 11, 2026

Sorted by Most popular

  1. vit-pytorchImplementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorchmit · linux25.5k
  2. TRLHugging Face’s Apache-2.0 trainers for SFT, DPO, PPO, and reward modeling.apache-2.0 · linux, macos, +119k
  3. PaLM-rlhf-pytorchImplementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLMmit · linux7.9k
  4. x-transformersA concise but complete full-attention transformer with a set of promising experimental features from various papersmit · linux5.9k
  5. audiolm-pytorchImplementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorchmit · linux2.6k
  6. alphafold3-pytorchImplementation of Alphafold 3 from Google Deepmind in Pytorchmit · linux1.7k
  7. soundstorm-pytorchImplementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorchmit · linux1.5k
  8. transfusion-pytorchPytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAImit · linux1.4k
  9. BS-RoFormerImplementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labsmit · linux935
  10. magvit2-pytorchImplementation of MagViT2 Tokenizer in Pytorchmit · linux668
  11. pi-zero-pytorchImplementation of π₀, the robotic foundation model architecture proposed by Physical Intelligencemit · linux584
  12. iTransformerUnofficial implementation of iTransformer - SOTA Time Series Forecasting using Attention networks, out of Tsinghua / Ant groupmit · linux541
  13. soft-moe-pytorchImplementation of Soft MoE, proposed by Brain's Vision team, in Pytorchmit · linux348
  14. clinical-calculator-tooluseExplorations into training LLMs to use clinical calculators from patient history, using open sourced models. Will start with Wells' Criteriamit · linux316
  15. nGPT-pytorchQuick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAImit · linux300
  16. simple-hierarchical-transformerExperiments around a simple idea for inducing multiple hierarchical predictive model within a GPTmit · linux228
  17. dreamer4Implementation of Danijar's latest iteration for his Dreamer line of workmit · linux215
  18. coconut-pytorchImplementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorchmit · linux184