On: Show HN: Web demo of 13B Alpaca-LLaMA trained on improved Stanford dataset

[sockeye]

Thanks!

- Training code is https://github.com/tatsu-lab/stanford_alpaca

- Params were mostly default (as in stanford_alpaca README), except for: per_device_train_batch_size=1, per_device_eval_batch_size=1

- Fine-tuning dataset was based on https://github.com/tloen/alpaca-lora/raw/81eb72f707b0505a03b... with minor improvements; I'm going to publish my version soon

- The training itself took about 3 hours on 8x Nvidia A100 80GB

[musabg → sockeye]

Where should we follow you so we immediately know when you published that?

[cglan → sockeye]

will you be publishing the trained 13b model?

[james7777 → sockeye]

if the 7b model took 3 hours with the same hardware and codes and parameters, how can the 13b model be done in 3 hours?