build1 publisher
250 Japanese labels put a 310M encoder 12 points ahead of a hosted decision API
On three Japanese tasks scored against the same 250 frozen rows, a fine-tuned encoder won topic classification by 12 points and tied both polarity tasks, while every zero-shot open-source model in the run lost all three.
Publishers:dev.to
Reality
- Evidence58
- Adoption15
- Hype gap−5
- Incentives45
- Confidence52