论文标题
Ruclip-新模型和实验：技术报告
RuCLIP -- new models and experiments: a technical report
论文作者
论文摘要
在报告中，我们提出了六个在24000万对培训的Ruclip模型的新实现。将精度结果与来自不同域的16个数据集上的Ru-en Translation（Opus-MT）的原始剪辑模型进行了比较。我们的最佳实现在大多数数据集中都超过了剪辑 + opus-MT解决方案，该解决方案在几个表和零摄像任务中。在报告中，我们简要描述了实现，并专注于进行的实验。推理执行时间比较也在报告中介绍。
In the report we propose six new implementations of ruCLIP model trained on our 240M pairs. The accuracy results are compared with original CLIP model with Ru-En translation (OPUS-MT) on 16 datasets from different domains. Our best implementations outperform CLIP + OPUS-MT solution on most of the datasets in few-show and zero-shot tasks. In the report we briefly describe the implementations and concentrate on the conducted experiments. Inference execution time comparison is also presented in the report.
