Mercity/bhagavad_gita-embeddings

Bhagavad Gita嵌入数据集是一个古印度史诗Bhagavad Gita的文本嵌入数据集，适用于自然语言处理任务、语义搜索和文本检索。每个数据条目包括唯一标识符、梵文原文、英文翻译以及使用BAAI/bge-large-en-v1.5和sentence-transformers/all-MiniLM-L6-v2模型生成的嵌入向量。The Bhagavad Gita Embedding Dataset is a specialized text embedding dataset of the ancient Indian epic, Bhagavad Gita, suitable for natural language processing tasks, semantic search, and text retrieval. Each entry in the dataset includes a unique identifier, the original Sanskrit text, the English translation, and vector representations generated using the BAAI/bge-large-en-v1.5 and sentence-transformers/all-MiniLM-L6-v2 models.