abacusai/Smaug-Llama-3-70B-Instruct

Smaug-Llama-3-70B-Instruct is a 70 billion parameter instruction-tuned causal language model developed by Abacus.AI, fine-tuned from Meta's Llama-3-70B-Instruct. Utilizing a novel 'Smaug recipe' for multi-turn conversations, it significantly outperforms its base model and achieves performance comparable to GPT-4-Turbo on MT-Bench. This model excels in conversational AI and general instruction following, making it suitable for advanced dialogue systems and complex query resolution.