Brinebreath-Llama-3.1-70B by gbueno86 is a 70 billion parameter language model based on the Llama 3.1 architecture, fine-tuned through a merge of several Llama 3.1 variants including Hermes-3, Dracarys, and SauerkrautLM. This model demonstrates a 7% overall success rate increase on MMLU-PRO compared to Meta-Llama-3.1-70B-Instruct, showing strong performance across various MMLU-PRO categories and improved results in programming and mathematical tasks during manual testing. It is optimized for enhanced reasoning and general knowledge tasks, making it suitable for applications requiring robust analytical capabilities.
No reviews yet. Be the first to review!
Hugging Face