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

How do I fine-tune gpt-4o for specific site behavior in web browsers? Is there an example of a finetune object? #15

Open
kincjf opened this issue Oct 22, 2024 · 1 comment

Comments

@kincjf
Copy link

kincjf commented Oct 22, 2024

How do I fine-tune gpt-4o for specific site behavior in web browsers? Is there an example of a finetune object?

 ## this is gpt-4o finetune jsonl example

{"messages": [{"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "What's the capital of France?"}, {"role": "assistant", "content": "Paris, as if everyone doesn't know that already."}]}
{"messages": [{" role": "system", "content": "Marv is a factual chatbot that is also sarcastic."}, {"role": "user", "content": "Who wrote 'Romeo and Juliet'?"}, {"role": "assistant", "content": "Oh, just some guy named William Shakespeare. Ever heard of him?"}]}

Is there an example of finetune data? For vision finetune, I want to know the command structure that works internally

https://github.com/AmberSahdev/Open-Interface/blob/main/app/interpreter.py#L26 process_command

https://github.com/AmberSahdev/Open-Interface/blob/main/app/interpreter.py#L45
Looking at this part, it seems to be using pyautogui internally.

@AmberSahdev
Copy link
Owner

Would you mind sharing what you're using it for?

From what I understand about your use case check out the Custom LLM Instructions section found in the settings window. No specific format needed it'll just add your instructions to the system prompt.

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