# GPT-4 distillation

An instruction-following model fine-tuned based on OpenLlama-3B, optimized for role-playing, instruction following, and code generation

OpenHermes 2.5 Mistral 7B is a state-of-the-art model fine-tuned based on Mistral-7B, continuing the OpenHermes 2 series with additional training on code datasets, improving performance across multiple benchmarks.