Functionary is a language model that can interpret and execute functions/plugins. The model determines when to execute functions, whether in parallel or serially, and can understand their outputs. It only triggers functions as needed. Function definitions are given as JSON Schema Objects, similar to OpenAI GPT function calls. — Intelligent parallel tool use — Able to analyze functions/tools outputs and provide relevant responses grounded in the outputs — Able to decide when to not use tools/call functions and provide normal chat response — Truly one of the best open-source alternative to GPT-4 Our model achieves achieves state-of-the-art performance in Function Calling Accuracy on our in-house dataset. The accuracy metric measures the overall correctness of predicted function calls, including function name prediction and arguments extraction. We use a specially designed prompt template which we call «v1PromptTemplate» that uses a variety of special tokens in each turn. We convert function definitions to a similar text to TypeScript definitions. Then we inject these definitions as system prompts. After that, we inject the default system prompt. Then we start the conversation…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: meetkai
Теги: mistral, conversational, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 20
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.