Closed riedgar-ms closed 3 months ago
Attention: Patch coverage is 83.33333%
with 2 lines
in your changes missing coverage. Please review.
Project coverage is 60.29%. Comparing base (
870a4f9
) to head (7bd6620
).
Files | Patch % | Lines |
---|---|---|
guidance/models/llama_cpp/_llama_cpp.py | 83.33% | 2 Missing :warning: |
:exclamation: Your organization needs to install the Codecov GitHub app to enable full functionality.
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
@mmoskal I do have the same tests implemented for some transformers
tokenisers in #899 ; those are working
I have also run a couple of the notebooks which use LlamaCpp models, and those have been fine as well.
There seems to be a bug in the
LlamaCpp
tokenisers, where they prepend spaces. Fix this following @mmoskal , by prepending a byte which is extremely unlikely to occur in a real string, and using it to figure out the offending prefix.