Description: The RA-IT-NER-zh-7B model is trained from Qwen1.5-7B using the proposed Retrieval Augmented Instruction Tuning (RA-IT) approach. This model can be used for Chinese Open NER with and without RAG. The training data is our constructed Sky-NER , an instruction tuning dataset for Chinese OpenNER. We follow the recipe of UniversalNER and use the large-scale SkyPile Corpus to construct this dataset. The data was collected by prompting gpt-3.5-turbo-0125 to label entities from passages and provide entity tags. The data collection prompt is as follows: Instruction: 给定一段文本，你的任务是抽取所有实体并识别它们的实体类别。输出应为以下JSON格式：[{«实体1»: «实体1的类别»}, …]。 Check our paper for more information. Check our github repo about how to use the model. The template for inference instances is as follows: Prompting template: USER: 以下是一些命名实体识别的例子：{Fill the NER examples here} ASSISTANT: 我已读完这些例子。 USER: 文本：{Fill the input text here} ASSISTANT: 我已读完这段文本。 USER: 文本中属于»{Fill the entity type here} «的实体有哪些？ ASSISTANT: (model’s predictions in JSON format) This model and its associated data are released under the CC BY-NC 4.0 license. They are primarily used for research purposes.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: EmmaStrong
Теги: qwen2, conversational, zh, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 32
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
