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

[PROPOSAL]: [chatgpt] add code for fine-tuning supervised model #3182

Closed
1 task done
pgzhang opened this issue Mar 20, 2023 · 2 comments · Fixed by #3183
Closed
1 task done

[PROPOSAL]: [chatgpt] add code for fine-tuning supervised model #3182

pgzhang opened this issue Mar 20, 2023 · 2 comments · Fixed by #3183
Labels
enhancement New feature or request

Comments

@pgzhang
Copy link
Contributor

pgzhang commented Mar 20, 2023

Proposal

Based on the instructions by InstructGPT, training the model involves three steps. ColossalAI has already implemented steps 2 and 3. Although there is code available for pretraining large language models (such as GPT) in this project, it does not fit well with ChatGPT. Therefore, I have written the code for step 1, which involves fine-tuning the model using supervised learning.

Self-service

  • I'd be willing to do some initial work on this proposal myself.
@pgzhang pgzhang added the enhancement New feature or request label Mar 20, 2023
@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿


Title: [PROPOSAL]: [chatgpt] add supervised learning fine-tune code

@pgzhang pgzhang changed the title [PROPOSAL]: [chatgpt] add supervised learning fine-tune code [PROPOSAL]: [chatgpt] add code for fine-tuning supervised model Mar 20, 2023
@ht-zhou
Copy link
Contributor

ht-zhou commented Mar 21, 2023

Fantastic work !! Thanks for your contribution !!
We will check your pr soon, and add ci about it.

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

Successfully merging a pull request may close this issue.

3 participants