Smith42

What would the selected participants get from this? Looks like there is no offer of funding?

The Multimodal Universe (MMU) pools together 80TB+ of data from over 30 astronomical surveys into one place. Crossmatching (linking observations of the same object across surveys) is its killer feature, but until now it required downloading hefty chunks of data to local disk. We got tired of needing a cluster just to run a crossmatch, so we gathered in the UniverseTBD and Hugging Science Discord servers to fix that. We've converted the MMU to the parquet-based HATS format so that you can use the LSDB and Hugging Face ecosystems to crossmatch from a laptop. The datasets are here https://huggingface.co/collections/UniverseTBD/multimodal-un.... No bulk downloads are necessary, and 4GB of RAM is enough even at Gaia scale.

It's always been this way ever since the first industrial revolution.

So write it! Shouldn't be much extra to add to the AGPL licence?

We investigate the potential constraints on LLM scaling posed by the availability of public human-generated text data. We forecast the growing demand for training data based on current trends and estimate the total stock of public human text data. Our findings indicate that if current LLM development trends continue, models will be trained on datasets roughly equal in size to the available stock of public human text data between 2026 and 2032, or slightly earlier if models are overtrained. We explore how progress in language modeling can continue when human-generated text datasets cannot be scaled any further. We argue that synthetic data generation, transfer learning from data-rich domains, and data efficiency improvements might support further progress.

That really isn't the case, and I am not sure how you could arrive at that unsubstantiated conclusion.

Abstract:

This work presents AstroPT, an autoregressive pretrained transformer developed with astronomical use-cases in mind. The AstroPT models presented here have been pretrained on 8.6 million 512 × 512 pixel grz-band galaxy postage stamp observations from the DESI Legacy Survey DR8. We train a selection of foundation models of increasing size from 1 million to 2.1 billion parameters, and find that AstroPT follows a similar saturating log-log scaling law to textual models. We also find that the models' performances on downstream tasks as measured by linear probing improves with model size up to the model parameter saturation point. We believe that collaborative community development paves the best route towards realising an open source `Large Observation Model' -- a model trained on data taken from the observational sciences at the scale seen in natural language processing. To this end, we release the source code, weights, and dataset for AstroPT under the MIT license, and invite potential collaborators to join us in collectively building and researching these models.

$15k!

"Large Observation Model" has a nice ring to it

If you are interested in this also check out EarthPT, which is also a time series decoding transformer (and has the code and weights released under the MIT licence): https://arxiv.org/abs/2309.07207

What's new with SXMO? Haven't been keeping up since 2021. Is there a stable phone to run this on now?

Wanted to share the code release of EarthPT, a model that predicts future satellite observations in a zero shot setting! I'm the first author so please shoot any questions you have at me.

EarthPT is a 700 million parameter decoding transformer foundation model trained in an autoregressive self-supervised manner and developed specifically with EO use-cases in mind. EarthPT can accurately predict future satellite observations across the 400-2300 nm range well into the future (we found six months!).

The embeddings learnt by EarthPT hold semantically meaningful information and could be exploited for downstream tasks such as highly granular, dynamic land use classification.

The coolest takeaway for me is that EO data provides us with -- in theory -- quadrillions of training tokens. Therefore, if we assume that EarthPT follows neural scaling laws akin to those derived for Large Language Models (LLMs), there is currently no data-imposed limit to scaling EarthPT and other similar ‘Large Observation Models.’(!)

Code: https://github.com/aspiaspace/EarthPT

Paper: https://arxiv.org/abs/2309.07207

Wishful thinkin buddy

Anyone have a paste of the article? There is a paywall

Check out EarthPT! https://arxiv.org/abs/2309.07207

This isn't the first foundation model for time series, see EarthPT from last month: https://arxiv.org/abs/2309.07207