mteb/PubChemSMILESBitextMining

ChemTEB是一个在化学领域数据上评估文本嵌入模型性能的数据集。它是一个MTEB数据集，用于评估模型在特定领域的性能和效率。数据集包括多种配置，如canon-desc、canon-title、iso-desc和iso-title，每个配置都有其对应的特征和分割。数据集的统计信息包括样本数量、字符数量、唯一对数、句子长度等。如果需要评估模型，可以使用mteb库中的相关代码进行操作。

ChemTEB is a dataset for evaluating the performance of text embedding models on chemical domain data. It is an MTEB dataset used to assess the performance and efficiency of models in a specific domain. The dataset includes various configurations such as canon-desc, canon-title, iso-desc, and iso-title, each with its corresponding features and splits. The datasets descriptive statistics include the number of samples, number of characters, unique pairs, sentence lengths, etc. To evaluate models, you can use the relevant code in the mteb library.