Bonito is an open-source model for conditional task generation: the task of converting unannotated text into task-specific training datasets for instruction tuning. Bonito can be used to create synthetic instruction tuning datasets to adapt large language models on users’ specialized, private data. In our paper, we show that Bonito can be used to adapt both pretrained and instruction tuned models to tasks without any annotations. — Developed by: Nihal V. Nayak, Yiyang Nan, Avi Trost, and Stephen H. Bach — Model type: MistralForCausalLM — Language(s) (NLP): English — License: TBD — Finetuned from model: mistralai/Mistral-7B-v0.1 — Repository: https://github.com/BatsResearch/bonito — Paper: Arxiv link To easily generate synthetic instruction tuning datasets, we recommend using the bonito package built using the transformers and the vllm libraries. Our model is trained to generate the following task types: summarization, sentiment analysis, multiple-choice question answering, extractive question answering, topic classification, natural language inference, question generation, text generation, question answering without choices, paraphrase identification, sentence completion, yes-no…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: alexandreteles
Теги: mistral, data generation, text2text-generation, en, text-generation-inference, endpoints_compatible, 4-bit, awq
Лайков: 3 | Загрузок: 23
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
