No description provided.

I just thought I'd suggest a model card.

Online Language Modelling org

Thanks! Your README is basically accurate with one addition: we also use a full october wikipedia snapshot to supplement the common crawl one. The model is actually still training, and we want to do a little more analysis when it is done too.

I'll discuss this in discord DMs, thank you so much for letting me know.

Online Language Modelling org

I'm closing this issue because I wrote a model card with results, etc. But I def appreciate this suggestion, and incorporated it into the bigger model card.

Tristan changed pull request status to closed

Sign up or log in to comment