Use logprobs in TLMChatCompletion #89
Open
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
jwmueller
reviewed
Jun 25, 2025
|
|
||
|
|
||
| def _extract_perplexity(response: "ChatCompletion") -> Optional[float]: | ||
| response_logprobs = response.choices[0].logprobs |
There was a problem hiding this comment.
this won't ever cause an error for any OpenAI LLM?
I'd imagine its safer to check if the key logprobs exists
There was a problem hiding this comment.
Afaik this always exists, I've encapsulated this entire function in a try / except block tho so even if something weird happens with extracting logprobs the entire call will not fail (it will just not include perplexity)
jwmueller
approved these changes
Aug 17, 2025
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Outdated suggestions cannot be applied.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.
No description provided.