This repository contains finetuned models from the paper Edisum: Summarizing and Explaining Wikipedia Edits at Scale. For more details see the home GitHub page.

The repo contains 5 models:

  • Edisum[0%] (edisum_0.ckpt)
  • Edisum[25%] (edisum_25.ckpt)
  • Edisum[50%] (edisum_50.ckpt)
  • Edisum[75%] (edisum_75.ckpt)
  • Edisum[100%] (edisum_100.ckpt)

Each one of those is trained on a mix of processed existing Wikipedia data and synthetically generated data (Edisum[n%] is trained on n% of synthetic data).

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train msakota/edisum