[Feature] Monitor token consumption #806
Merged
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
riedgar-ms
commented
May 7, 2024
riedgar-ms
commented
May 7, 2024
riedgar-ms
commented
May 7, 2024
Codecov ReportAttention: Patch coverage is
❗ Your organization needs to install the Codecov GitHub app to enable full functionality. Additional details and impacted files@@ Coverage Diff @@
## main #806 +/- ##
==========================================
+ Coverage 56.72% 62.14% +5.42%
==========================================
Files 56 57 +1
Lines 4159 4174 +15
==========================================
+ Hits 2359 2594 +235
+ Misses 1800 1580 -220 ☔ View full report in Codecov by Sentry. |
riedgar-ms
changed the title
|
LGTM |
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Outdated suggestions cannot be applied.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.
Count tokens fed into & retrieved from the underlying LLM. This is just for Tranformer and LLamaCpp models at the current time.
This hooks into
get_logits()which is the method which concreteEngines must implement. We don't attempt to distinguish between 'forced' and 'prompt' tokens. Between non-unique tokenisations, a variety of tokenisers and token healing, trying to count tokens exactly is decidedly non-trivial.