We value your privacy
This site uses cookies to improve your browsing experience, analyze site traffic, and show personalized content.
A NEW FRONTIER MODEL OF OPEN SOURCE AI Our training data aggressively encourages the model to follow the system and instruction prompts exactly and in an adaptive manner. Hermes 3 was created by fine-tuning Llama 3.1 8B, 70B and 405B, and training on a dataset of primarily synthetically generated responses. The model boasts comparable and superior performance to Llama 3.1 while unlocking deeper capabilities in reasoning and creativity. Experiment, and push the boundaries of individual-alignment, artificial consciousness, open-source software!