Nous Hermes

Nous Research's fine-tuned open-source models for instruction following

Code & DevelopmentFree

Nous Hermes is a series of fine-tuned language models from Nous Research that excel at instruction following, reasoning, and code generation. Built on Llama, Mistral, and other base models, Hermes models are trained on high-quality synthetic and curated datasets to produce more reliable, thoughtful responses than base models. Nous Hermes 3 Llama 3.1 405B is one of the top-ranked open-source instruction models on Hugging Face's open LLM leaderboard.

Key Features

• ✓Multiple base models
• ✓Top instruction following
• ✓Reasoning benchmarks
• ✓Open weights
• ✓Fine-tuning recipes
• ✓Community supported