If you care about having both the instruction-finetuned variant and the base model, I think I’d go with one of the smaller LLaMAs (7B/13B). Importantly, they fit on one 40⁄80 GB A100 comfortably, which saves a lot of hassle. There’s also a bajillion fine-tuned versions of them if you want to experiment.
If you care about having both the instruction-finetuned variant and the base model, I think I’d go with one of the smaller LLaMAs (7B/13B). Importantly, they fit on one 40⁄80 GB A100 comfortably, which saves a lot of hassle. There’s also a bajillion fine-tuned versions of them if you want to experiment.