Will instruction fine tuned models be made available as well

[allthingssecurity]

Will instruction fine tuned models be made available as well for this

[conceptofmind]

@allthingssecurity All instruction-finetuned models on FLAN will be made publicly available as well.

[allthingssecurity]

Thanks for such a quick reply. When can we expect the same?

[conceptofmind]

Thanks for such a quick reply. When can we expect the same?

The 2.1b model is training now. 2b won't be done for days. So after that finishes I will start training all of the flan-PaLM models.

[allthingssecurity]

Please let me know if I can help. I can dedicate some compute for it. Have already done some finetuning for Flan models in past

[Njasa2k]

Will there be bigger models than 2B?

[conceptofmind]

Will there be bigger models than 2B?

That is largely dependent on whether CarperAI and StabilityAI want to pursue larger training runs for PaLM. I can say that there is a plan to train a much larger Sparrow model similar to PaLM with RLHF on more tokens.

You can join the CarperAI discord to follow the projects: https://discord.gg/canadagoose

[varunnathan]

Hello Team,

First of all, great work and this is super helpful for the open source community.
I wanted to check if there are any updates on the instruction fine-tuned models?

Thanks.

[conceptofmind]

I do not have access to any gpus. So no models will be trained.