eekay/gemma-2b-it-cat-pref-ft-numbers
收藏官方服务：
资源简介：
该数据集用于训练名为eekay/gemma-2b-it-cat-pref-ft的语言模型，模型类型为hf。数据集包含30000个示例，使用google/gemma-2b-it作为分词器。训练过程中，每个批次大小为256，最多生成64个新标记。答案计数为10，每个答案最多有3位数字。具体的数据集内容描述未在README中提供。
The dataset is used for training the language model named eekay/gemma-2b-it-cat-pref-ft, with the model type being hf. It contains 30000 examples and uses google/gemma-2b-it as the tokenizer. During training, the batch size is 256, and up to 64 new tokens can be generated. The answer count is 10, with each answer having a maximum of 3 digits. Specific details about the dataset content are not provided in the README.
提供机构：
eekay
