google-research / jestimatorLinks
Amos optimizer with JEstimator lib.
☆82Updated last year
Alternatives and similar repositories for jestimator
Users that are interested in jestimator are comparing it to the libraries listed below
Sorting:
- HomebrewNLP in JAX flavour for maintable TPU-Training☆50Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆189Updated 3 years ago
- A case study of efficient training of large language models using commodity hardware.☆68Updated 3 years ago
- Automatically take good care of your preemptible TPUs☆36Updated 2 years ago
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …☆115Updated last year
- ☆31Updated 3 months ago
- Train very large language models in Jax.☆209Updated last year
- My explorations into editing the knowledge and memories of an attention network☆35Updated 2 years ago
- ☆62Updated 3 years ago
- ☆67Updated 3 years ago
- some common Huggingface transformers in maximal update parametrization (µP)☆82Updated 3 years ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆81Updated 3 years ago
- A library to create and manage configuration files, especially for machine learning projects.☆79Updated 3 years ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆135Updated last year
- GPT, but made only out of MLPs☆89Updated 4 years ago
- ☆363Updated last year
- ☆66Updated 3 years ago
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆207Updated 2 years ago
- LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence☆59Updated 3 years ago
- JAX implementation of the Llama 2 model☆218Updated last year
- ☆189Updated last week
- Official code for "Distributed Deep Learning in Open Collaborations" (NeurIPS 2021)☆117Updated 3 years ago
- gpu tester detects broken and slow gpus in a cluster☆72Updated 2 years ago
- ☆166Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- git extension for {collaborative, communal, continual} model development☆215Updated 10 months ago
- LoRA for arbitrary JAX models and functions☆142Updated last year
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated 2 years ago
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆87Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆90Updated last year