anthracite-org/magnum-v3-27b-kto

The anthracite-org/magnum-v3-27b-kto is a 27 billion parameter language model developed by Anthracite, fine-tuned on top of IntervitensInc/gemma-2-27b-chatml. This model is the 12th in a series designed to replicate the prose quality of Claude 3 models, specifically Sonnet and Opus. It was developed using multiple KTO runs on top of an SFT run, focusing on enhancing prose generation. The model is instruction-tuned with ChatML formatting and has a context length of 32768 tokens, making it suitable for detailed conversational and creative writing tasks.