245 add repetition penalties to generate #246
Merged
Conversation
This file contains hidden or 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
Add possible repetition penalty code to NotGPT.generate() ...
Possibly complete on repetition penalties.
Apply repetition_penalty on generation samples with sampling.
Trigger workflow to run.
Added a punitive frequency_penalty to hopefully cut the successive repetition of a word word word ....
Raise frequency_penalty and add a presence penalty also.
Add debug prints to introspect sampling.
Try a repetition_penalty of 1.2.
Lower top_p. Often there is only 1 word to sample from.
Set top_p to 0.98 meant to raise, lowered by mistake lol ....
Increase top_p to add more diversity.
Add back separate frequency and presence penalties.
david-thrower
merged commit 93e7284
into
240-branch-to-diverge-cicd-scale-nlp-hpo-from-at-scale-study
1 check passed
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Outdated suggestions cannot be applied.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.
Added penalties for repetition.