Сбалансированная версия линейки Hermes 3, предлагающая золотую середину между мощностью и скоростью работы. Модель идеально подходит для роли умного ИИ-ассистента, демонстрируя высокую точность в ответах и гибкость при выполнении сложных инструкций в чат-ботах.
Instruct (or “chat”) tuned models have become the primary way in which most people interact with large language models. As opposed to “base” or “foundation” models, instruct-tuned models are optimized to respond to imperative statements. We present Hermes 3, a neutrally-aligned generalist instruct and tool use model with strong reasoning and creative abilities. Its largest version, Hermes 3 405B, achieves state of the art performance among open weight models on several public benchmarks. The weights for all models are available at https://huggingface.co/NousResearch.