I have a question?
What differences are between meta-llama/Meta-Llama-3-8B and meta-llama/Meta-Llama-3-8B-instruct?
Hello, I just checked the documentation for Meta-Llama-3-8B and in the Variants section it mentions that the model comes in two versions: Pre-trained and instruction tuned. I’m guessing Meta-Llama-3-8B is the pre-trained version (with no fine-tuning) and the Meta-Llama-3-8B-instruct is the instruction tuned variant that is fine-tuned on instructions. Hope this helps!