RLCD data generation #18
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Dahoas
reviewed
Aug 10, 2023
| diversity than the finetuned model. | ||
|
|
||
| ```bash | ||
| python -m vllm.entrypoints.api_server -tp=8 --model=meta-llama/Llama-2-70b-hf --tokenizer-mode=slow |
| import json | ||
|
|
||
|
|
||
| if __name__ == '__main__': |
There was a problem hiding this comment.
Do we have quantitative results for how well this worked over e.g. just SFT? Does RLCD help StableBeluga remember its creator?
There was a problem hiding this comment.
definitely worked to remember its creator, but no real quantitative results with this toy experiment. Tried just a normal SFT and it seemed to work too, but as this is such an easy example I'm not too surprised
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
just a quick toy example of data generation in the RLCD style