[staticman2]

I'm talking about taking the Llama 3 base model and finetuning it with a dataset that doesn't include refusals, not whatever you mean by "taking a model that's already been lobotomized".

It's interesting that you weren't convinced by the above argument but still repeated the edgelord term "lobotomized" in your reply.

[errantspark]

The claim is that llama is "lobotomized" because it was trained with safety in mind. You can't untrain that by finetuning. For what it's worth the non-instruct llama generally seems better at reasoning than instruct llama which i think is a point in support of OP.

[staticman2]

Better at reasoning based on benchmarks or what?