Closed lintool closed 2 months ago
All modified and coverable lines are covered by tests :white_check_mark:
Project coverage is 67.17%. Comparing base (
98e4866
) to head (f5d624f
).
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
This is interesting. Does this happen for tokenizers trained & stored locally and tokenizers attached to models on HF?
This is interesting. Does this happen for tokenizers trained & stored locally and tokenizers attached to models on HF?
- Tagging @ToluClassics for thoughts.
Not sure. In this PR are all the scores that changed. Everything else didn't.
I took a look and tested it with the GPT-2 tokenizer. The DJL implementation doesn't use the modelMaxLength, even if it is set in the tokenizer_config.json.
Supersede by #2536 which is the better solution.
Recent upgrade to DJL v0.28.0 #2529 caused a bunch of score differences related to underlying use of hgf tokenizers.
Documented in code, but extracting here for visibility: