lessw2020 / transformer_central
Various transformers for FSDP research
☆33Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for transformer_central
- A place to store reusable transformer components of my own creation or found on the interwebs☆44Updated 2 weeks ago
- Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers☆58Updated 4 months ago
- HomebrewNLP in JAX flavour for maintable TPU-Training☆46Updated 10 months ago
- ☆20Updated last year
- ☆57Updated 2 years ago
- ☆77Updated 5 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆35Updated 4 months ago
- ☆73Updated 4 months ago
- ☆20Updated last year
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆92Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆76Updated 2 years ago
- This repository contains example code to build models on TPUs☆30Updated last year
- Experiment of using Tangent to autodiff triton☆72Updated 9 months ago
- My explorations into editing the knowledge and memories of an attention network☆34Updated last year
- A library for squeakily cleaning and filtering language datasets.☆45Updated last year
- ☆29Updated 2 years ago
- A fast implementation of T5/UL2 in PyTorch using Flash Attention☆71Updated last month
- A dashboard for exploring timm learning rate schedulers☆18Updated last year
- Utilities for Training Very Large Models☆56Updated last month
- ☆13Updated last year
- Automatically take good care of your preemptible TPUs☆32Updated last year
- Scalable and Performant Data Loading☆66Updated this week
- Training and evaluation code for the paper "Headless Language Models: Learning without Predicting with Contrastive Weight Tying" (https:/…☆23Updated 7 months ago
- A library for unit scaling in PyTorch☆105Updated 2 weeks ago
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated last year
- RWKV model implementation☆38Updated last year