StepanTita/space-model

Space Model framework that allows for maintaining generalizability, and enhances the performance on the downstream task by utilizing task-specific context attribution. It is an external LLM layer, that improves accuracy in classification task for multiple datasets, such as HateXplain, IMDB movies reviews and more.

语言：HTML · GitHub 星标：9 · Fork：0

话题：bert-embeddings · bert-fine-tuning · bert-model · classification · distilbert · embeddings · fine-tuning · large-language-models

在 GitHub 上查看原仓库