Do we know how the compute that BlenderBot uses compares to ChatGPT?
Is ChatGPTs advantage due to using more compute or due to the underlying system being more efficient?
Facebooks models use maybe 1⁄4 the compute (rough guess) and have more implementation issues and worse finetuning
Do we know how the compute that BlenderBot uses compares to ChatGPT?
Is ChatGPTs advantage due to using more compute or due to the underlying system being more efficient?
Facebooks models use maybe 1⁄4 the compute (rough guess) and have more implementation issues and worse finetuning