minus-squareAdOne8437@alien.topBtoLocalLLaMA•Chassis only has space for 1 GPU - Llama 2 70b possible on a budget?linkfedilinkEnglisharrow-up1·3 years agoWhat model did you use and what model loader? linkfedilink
minus-squareAdOne8437@alien.topBtoLocalLLaMA•What prompts/questions do you use to test a model’s capabilities? Ideally ones that aren’t included in their training data.linkfedilinkEnglisharrow-up1·3 years agoI fear this one will be part of the training/finetune data very soon. linkfedilink
minus-squareAdOne8437@alien.topBtoLocalLLaMA•Nouse-Capybara-34B 200KlinkfedilinkEnglisharrow-up1·3 years agoif it is based in yi, should it not have the yi-licence instead of mit? linkfedilink
What model did you use and what model loader?