lucaslingle / mu_transformer
Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.
☆30Updated this week
Alternatives and similar repositories for mu_transformer:
Users that are interested in mu_transformer are comparing it to the libraries listed below
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆17Updated last month
- Automatically take good care of your preemptible TPUs☆36Updated last year
- Minimal but scalable implementation of large language models in JAX☆34Updated 5 months ago
- Code for the paper "Function-Space Learning Rates"☆19Updated last week
- some common Huggingface transformers in maximal update parametrization (µP)☆80Updated 3 years ago
- ☆30Updated 5 months ago
- An implementation of the Llama architecture, to instruct and delight☆21Updated 3 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆45Updated 9 months ago
- JAX implementation of the Mistral 7b v0.2 model☆35Updated 9 months ago
- Jax like function transformation engine but micro, microjax☆30Updated 6 months ago
- Triton Implementation of HyperAttention Algorithm☆47Updated last year
- ☆19Updated 3 weeks ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆87Updated 10 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆123Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆83Updated last year
- Implementation of PSGD optimizer in JAX☆31Updated 3 months ago
- ☆52Updated 6 months ago
- ☆21Updated 4 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆24Updated 3 months ago
- Mobile Viewer for W&B, built on top of Flutter.☆33Updated last year
- This repo is based on https://github.com/jiaweizzhao/GaLore☆26Updated 7 months ago
- ☆78Updated 9 months ago
- ☆53Updated last month
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆55Updated 11 months ago
- Make triton easier☆47Updated 10 months ago
- ☆20Updated last year
- ☆17Updated 8 months ago
- Here we will test various linear attention designs.☆60Updated last year
- A flexible and efficient implementation of Flash Attention 2.0 for JAX, supporting multiple backends (GPU/TPU/CPU) and platforms (Triton/…☆23Updated last month
- RWKV model implementation☆37Updated last year