Animal House

2 readers

1 users here now

Discussion area for the main blog: animal-machine.com. Feel free to comment here to discuss any of my blog posts.

Rules:

Excessive hate speech such racism will not be tolerated.
Excessive self-promotion or advertisement will probably get modded.
Try to be kind where possible. At the very least, be respectful when disagreeing.

founded 1 year ago

MODERATORS

[email protected]

I've successfully generated my own dataset and finetuned a LLM on it! (lemmy.animal-machine.com)

submitted 1 year ago by [email protected] to c/[email protected]

1 comments fedilink hide all child comments

Holy crap! I've finally done it. I've generated a dataset of conversations (all locally), cleaned them up and then finetuned it on open-llama-7b (just to test) and IT WORKED! AHHHHH! happy noises

Okay I gotta go to sleep now. I have to get up for work in less than five hours. I'll be cleaning up everything, commiting code and doing the write up this week.

top 1 comments

sorted by: hot top controversial new old

[–] [email protected] 1 points 1 year ago

I'm just too tired to deal with writing up everything until Friday, since I have a lot of hours at my day job this week.

But, if by chance anyone is watching this, you can see the code that I checked into the dev branch of Kontour and the configuration file used to generate the datasets I used as well as the scripts in data-cleaning to reformat everything.

https://github.com/tbogdala/kontour/tree/dev