Open czlr opened 3 months ago
For the 70B model, it may take 131GB
And 15GB for the 8B model. The regular and instruct are equal in size, but the latter is finetuned toward chat and is safer(less toxic).
I have a related question: if the model has 70B parameters, wouldn't we expect the size of the model to be 70*4=280 GB? A Float32 parameter takes up 4 bytes of storage. Are the parameters of LLaMA Float16-numbers?
I think that you have misunderstood the 'B' in the 70B. Actually, it means billion.
@vonpetersenn Yes they are float16 -- specifically "bf16" (Brain Float 16) format.
thank you very much!
Request: As a casual user without much knowledge in LLMs, it would be nice to know upfront how much disk space the models need.
Currently: The various posts and docs only mention that llama 3.1 comes in different variants: 8B, 70B, 405B; regular vs instruct; etc. But they don't mention things like required disk size usage, or minimum system specs to run things smoothly. (Unless I accidentally missed those details) I can only start a download blindly and monitor while it's going. The 70B model also seems to come in 17GB .pth parts -- I can't see how many parts are remaining either.