Fix prompt length calculation #548
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
|
Better to check the model and then calc. gpt3.5 and 4 seems calc differently. |
|
I also make the change in #546, but your code looks better 😀 |
|
after test, at least in gpt-3.5, tokens_per_message is 5. I think it's one missing |
hexiaokang
approved these changes
May 2, 2023
|
Is there anyone to merge or review this pr? |
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Outdated suggestions cannot be applied.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.
Current
_buildMessages()calculates tokens in prompt in a wrong way - there's a small difference with a usage amount that comes from ChatGPT (in non-stream mode).I fix it, picking the logic from here
Now our estimated
numTokensshould be equal tomessage.detail.usage.prompt_tokens