Hermes 3 Technical Report
This work addresses the need for accessible, high-quality instruct-tuned models for general users, though it appears incremental as it builds on existing tuning approaches.
The authors tackled the problem of creating a high-performing instruct-tuned large language model, resulting in Hermes 3 405B achieving state-of-the-art performance among open weight models on several public benchmarks.
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.