Training Transformers Together · HackerPapers discussions

Training Transformers Together — mentioned by lucidrains

Sat, 04 Feb 2023 18:37:50 GMT

you are probably thinking of https://arxiv.org/abs/2207.03481 for inference, there is https://github.com/bigscience-workshop/petals however, both are only in the research phase. start tinkering!

Paper and discussion history. A mention is not an endorsement.

Training Transformers Together — mentioned by sanxiyn

Sat, 10 Sep 2022 01:59:07 GMT

Likely yes, it already has been done for DALL-E. Have a look at Training Transformers Together for what is involved: https://arxiv.org/abs/2207.03481.

Paper and discussion history. A mention is not an endorsement.