Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Make crear, that you can theoretically train your own LLM models #5

Open
robinmanuelthiel opened this issue Aug 3, 2023 · 1 comment
Assignees

Comments

@robinmanuelthiel
Copy link
Member

The text says, I can't bring my own data into an LLM because the models are pre-trained, so the only way to get more information in is to retrain the model, which is an expensive and time consuming process.

"The thing is, you can't actually do that. The models are pre-trained, so the only way to get more information in is to retrain the model, which is an expensive and time consuming process.\n",

So this statement is contradictory. I can do it, it's just very expensive and resource intensive and time consuming. I suggest to adjust that to avoid confusion.

@robinmanuelthiel robinmanuelthiel changed the title Make crearer, that you _can_ theoretically train your own LLM models Make crear, that you can theoretically train your own LLM models Aug 3, 2023
@MarkWme MarkWme self-assigned this Aug 4, 2023
@MarkWme
Copy link
Member

MarkWme commented Aug 4, 2023

Yes, I get that the statement is a little confusing. Just trying to convey that you can't add your own data to the existing models that the AI is using, but you can use techniques to achieve something similar, which is what embeddings are for. Will look at rewording this. Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants