Marin

marin.community · 166 words · saved by 10 readers

Marin is an open lab for building foundation models—together. We’re training powerful models from scratch, and sharing and programmatically documenting every step: the code, the data, the experiments, the mistakes…all in real-time. We invite anyone who shares our vision of open science and open-source to join and contribute, whether you want to try out a new architecture, training algorithm, dataset, evaluation…there is a lot to do! To learn more about the vision, read our launch announcement. Want to jump in? Install the Marin code and run your first experiment! Want to stay up to date? Join our Discord or our mailing list. Building a foundation model requires countless experiments trying out endless variants of algorithms and datasets. All the experiments we’re doing are captured as GitHub issues (here is a summary). Here’s the lifecycle of an experiment: Some examples: We trained some models in Marin: Have a new architecture or training procedure that you think is more efficient? Pa

To do this, we are discovering and assembling the knowledge required to build artificial intelligence and returning it to the world. Open means that we share everything: Our discussions (join here) All of our code, including models, infrastructure, etc. Our models' weights The sources of all the data in our training corpus The results of our successful and unsuccessful experiments Tools that make it easy to learn from this effort Marin is primarily developed by Open Athena , with contributors from the community. This work is generously supported by the Google TPU Research Cloud…

Marin

saved by

related reading