Bonito is an open-source model for conditional task generation that converts unannotated text into task-specific instruction tuning datasets. It enables zero-shot task adaptation of large language models on users' specialized, private data. Bonito is trained on a large-scale dataset created by remixing existing instruction tuning datasets into meta-templates. These meta-templates generate training examples where the input is unannotated text and the task attribute, and the output consists of the instruction and the response. Bonito is used to generate synthetic tasks for seven datasets from specialized domains with unannotated text across three task types—yes-no question answering, extractive question answering, and natural language inference. The results show that Bonito significantly improves the average performance of pretrained and instruction-tuned models over the de facto self-supervised baseline. For example, adapting Mistral-Instruct-v2 and instruction-tuned variants of Mistral and Llama2 with Bonito improves the strong zero-shot performance by 22.1 F1 points whereas the next word prediction objective undoes some of the benefits of instruction tuning and reduces the average performance by 0.8 F1 points. Additional experiments show that Bonito improves performance across different domains and training sizes. Bonito generates high-quality tasks that can be used to adapt language models to new domains. The model, dataset, and code are available at https://github.com/BatsResearch/bonito.Bonito is an open-source model for conditional task generation that converts unannotated text into task-specific instruction tuning datasets. It enables zero-shot task adaptation of large language models on users' specialized, private data. Bonito is trained on a large-scale dataset created by remixing existing instruction tuning datasets into meta-templates. These meta-templates generate training examples where the input is unannotated text and the task attribute, and the output consists of the instruction and the response. Bonito is used to generate synthetic tasks for seven datasets from specialized domains with unannotated text across three task types—yes-no question answering, extractive question answering, and natural language inference. The results show that Bonito significantly improves the average performance of pretrained and instruction-tuned models over the de facto self-supervised baseline. For example, adapting Mistral-Instruct-v2 and instruction-tuned variants of Mistral and Llama2 with Bonito improves the strong zero-shot performance by 22.1 F1 points whereas the next word prediction objective undoes some of the benefits of instruction tuning and reduces the average performance by 0.8 F1 points. Additional experiments show that Bonito improves performance across different domains and training sizes. Bonito generates high-quality tasks that can be used to adapt language models to new domains. The model, dataset, and code are available at https://github.com/BatsResearch/bonito.