LoRA Land's 27 fine-tuned #opensource #mistral-7b #LLMs no only rival #GPT-4, but they're also very cost-effective! Assuming 2M tokens (90% input; 10% output) per adapter per day, you can cut inference costs by 45%-65% vs. GPT-3.5 Turbo and 97%-98% vs. GPT-4 Turbo

→ View original post on X — @predibase,