Hacker News new | past | comments | ask | show | jobs | submit login

I intend to productionize text generation, and this is a necessary intermediate step. (gpt-2-simple had too many issues in this area so I needed to start from scratch)



That is cool, do you have a timeline set out for this?


I'll likely start by creating a web API service similar to what I did for gpt-2-simple, except more efficient: https://github.com/minimaxir/gpt-2-cloud-run

The next step is architecting an infrastructure for scalable generation; that depends on a few fixes for both aitextgen and the base Transformers. No ETA.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: