Быстрый Bert для Semantic text similarity (STS) на CPU
Быстрая модель BERT для расчетов компактных эмбедингов предложений на русском языке. Модель основана на
cointegrated/rubert-tiny2
- имеет аналогичные размеры контекста (2048), ембединга (312) и быстродействие. Является первой и самой быстрой моделью в серии BERT-STS.
На STS и близких задачах (PI, NLI, SA, TI) для русского языка превосходит по качеству LaBSE. Для работы с контекстом свыше 512 токенов требует дообучения под целевой домен.
Выбор модели из серии BERT-STS (качество/скорость)
rubert-tiny-sts huggingface.co is an AI model on huggingface.co that provides rubert-tiny-sts's model effect (), which can be used instantly with this sergeyzh rubert-tiny-sts model. huggingface.co supports a free trial of the rubert-tiny-sts model, and also provides paid use of the rubert-tiny-sts. Support call rubert-tiny-sts model through api, including Node.js, Python, http.
rubert-tiny-sts huggingface.co is an online trial and call api platform, which integrates rubert-tiny-sts's modeling effects, including api services, and provides a free online trial of rubert-tiny-sts, you can try rubert-tiny-sts online for free by clicking the link below.
sergeyzh rubert-tiny-sts online free url in huggingface.co:
rubert-tiny-sts is an open source model from GitHub that offers a free installation service, and any user can find rubert-tiny-sts on GitHub to install. At the same time, huggingface.co provides the effect of rubert-tiny-sts install, users can directly use rubert-tiny-sts installed effect in huggingface.co for debugging and trial. It also supports api for free installation.