They make good classifiers when fine tuned | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		potatoman22 on Oct 11, 2023 \| parent \| context \| favorite \| on: M2 Ultra can run 128 streams of Llama 2 7B in para... They make good classifiers when fine tuned

eurekin on Oct 11, 2023 | [–]

Interesting!

I'd have one use case for classification: user text (from a jira issue) mapped to the team responsible for the fix.

Can you share some tutorials? I only just managed to get this working on windows/cuda:

https://colab.research.google.com/drive/1vk8i01apaSp59GVV2yI...

It's been a royal pain to setup

objektif on Oct 12, 2023 | [–]

Do you have any pointers to learn how to start with fine tuning mistral locally!

cypress66 on Oct 12, 2023 | [–]

Use axolotl

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