flammenai/Flammades-Mistral-Nemo-12B

Flammades-Mistral-Nemo-12B is a 12 billion parameter language model developed by flammenai, built upon the nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2 base model. It was fine-tuned using ORPO on specific DPO datasets, including flammenai/Date-DPO-NoAsterisks and jondurbin/truthy-dpo-v0.1, to enhance its conversational and truthfulness capabilities. With a context length of 32768 tokens, this model is designed for general-purpose text generation and understanding, particularly benefiting from its DPO-tuned alignment.