some common Huggingface transformers in maximal update parametrization (µP)
☆87Mar 14, 2022Updated 4 years ago
Alternatives and similar repositories for mutransformers
Users that are interested in mutransformers are comparing it to the libraries listed below
Sorting:
- maximal update parametrization (µP)☆1,690Jul 17, 2024Updated last year
- Code for the paper "Function-Space Learning Rates"☆25Jun 3, 2025Updated 9 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated 7 months ago
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆32Jun 5, 2025Updated 9 months ago
- AGiXT is a dynamic AI Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse A…☆23Jan 26, 2026Updated last month
- Efficient Hyper-parameter Tuning at Scale (VLDB'22)☆10Dec 1, 2021Updated 4 years ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆226Sep 18, 2025Updated 6 months ago
- Code for Augment & Reduce, a scalable stochastic algorithm for large categorical distributions☆10May 16, 2018Updated 7 years ago
- Token-free Language Modeling with ByGPT5 & Friends!☆12Jul 18, 2025Updated 8 months ago
- [ICLR 2026 🔥] Dr.LLM: Dynamic Layer Routing in LLMs☆44Oct 15, 2025Updated 5 months ago
- Optimizing bit-level Jaccard Index and Population Counts for large-scale quantized Vector Search via Harley-Seal CSA and Lookup Tables☆21May 18, 2025Updated 10 months ago
- Minimal but scalable implementation of large language models in JAX☆35Nov 28, 2025Updated 3 months ago
- QLoRA for Masked Language Modeling☆23Sep 11, 2023Updated 2 years ago
- Comparison between GFlowNets & Maximum Entropy RL☆19Feb 19, 2024Updated 2 years ago
- HomebrewNLP in JAX flavour for maintable TPU-Training☆51Jan 20, 2024Updated 2 years ago
- Pytorch optimiser for training ANNs with exponentiated gradient desent☆20Mar 20, 2025Updated last year
- This repository contains the code for paper Prompting ELECTRA Few-Shot Learning with Discriminative Pre-Trained Models.☆48Jun 7, 2022Updated 3 years ago
- Maximal Update Parametrization (μP) with Flax & Optax.☆16Dec 27, 2023Updated 2 years ago
- The repository for the code of the UltraFastBERT paper☆519Mar 24, 2024Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆190Jan 19, 2026Updated 2 months ago
- Code repository for the c-BTM paper☆108Sep 26, 2023Updated 2 years ago
- ☆38Aug 7, 2025Updated 7 months ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆86Jul 28, 2024Updated last year
- ☆16Jul 29, 2025Updated 7 months ago
- ☆20Nov 18, 2024Updated last year
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Jul 12, 2023Updated 2 years ago
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆36Jun 7, 2024Updated last year
- The contrastive token loss function for reducing generative repetition of autoregressive neural language models.☆13May 11, 2022Updated 3 years ago
- 📰 Computing the information content of trained neural networks☆23Oct 8, 2021Updated 4 years ago
- Kyurae Kim's Awesome Reads☆20Nov 20, 2024Updated last year
- alternative way to calculating self attention☆18May 25, 2024Updated last year
- A repository for log-time feedforward networks☆224Apr 9, 2024Updated last year
- Alpha-Zero Connect Four NN trained via self play☆26Mar 7, 2025Updated last year
- ☆167Jul 5, 2023Updated 2 years ago
- ☆21Mar 7, 2023Updated 3 years ago
- A from-scratch neural network and transformers library, with speeds rivaling PyTorch☆10Mar 16, 2025Updated last year
- A port of muP to JAX/Haiku☆25Oct 23, 2022Updated 3 years ago
- Korean Math Word Problems☆59Jan 14, 2022Updated 4 years ago
- seqax = sequence modeling + JAX☆187Jul 23, 2025Updated 8 months ago