Mistral’s 8x7B Mixture of Experts (MoE) outperforms the Llama2 70B!
This video walkthrough is simple to follow and uses QLoRA, so you don’t need an A100
YouTube link is located 🤙 below (from @HarperSCarroll)
Mistral’s 8x7B Mixture of Experts (MoE) outperforms the Llama2 70B!
This video walkthrough is simple to follow and uses QLoRA, so you don’t need an A100
YouTube link is located 🤙 below (from @HarperSCarroll)