Sotiris Anagnostidis comments

Results 39 comments of


                                            Sotiris Anagnostidis

Try Supervised Fine-Tuning on pseudo-QA-data

Partially resolved in [PR](https://github.com/LAION-AI/Open-Assistant/pull/301).

Try Supervised Fine-Tuning on pseudo-QA-data

@ekurtulus there are a few things/plans on in the discord server. I am not sure if I have seen you there :))

Try Supervised Fine-Tuning on pseudo-QA-data

Mostly yes, we can sync from there!

Try Supervised Fine-Tuning on pseudo-QA-data

@lakshaykc what is your discord name? I can give you more access I believe

Try Supervised Fine-Tuning on pseudo-QA-data

The original purpose of the issue I think is served. See #619 for latest updates on the code. Once we get the human data we will continue on supervised fine-tuning...

Few-shot prefix a LLM to prompt it into an instruction following mode

Feel free to join the discord and contact me from there :)

Few-shot prefix a LLM to prompt it into an instruction following mode

Thanks for the effort @Abubakar115e. The idea of this issue is to experiment with different prefixes. If you cannot run these models it would be difficult to proceed. Perhaps you...

Few-shot prefix a LLM to prompt it into an instruction following mode

That's me: Sotiris#3996 :)

Fix summarize from human feedback dataset source

We can remove this if fixed from #352

A more general support for QA and summarization (review and feedback needed)

Looks good, after the merge! Do you know which models use the SAM optimizer?