Yep, the 50x cost reduction is if you self-host a fine-tuned model using the set...

light | darkhn

		kcorbitt on Sept 12, 2023 \| parent \| context \| \| on: Fine-tune your own Llama 2 to replace GPT-3.5/4 Yep, the 50x cost reduction is if you self-host a fine-tuned model using the setup demonstrated in in the linked notebooks.