Request for model definition

#5
by AvDy - opened

Hi,

Thank you for your great work. If possible, I request you to also provide the model definition for this pretrained model. As mentioned, it is using a LLaMA3 8B model, but I assume that some of the functions have been changed for the quantization purposes.

Hugging Face 1Bit LLMs org

Hello, The model definition is the same as a Llama3 8B, the only difference is Linear layers are replaced with BitLinear layers. You can refer to the blogpost here to understand how BitLinear works

medmekk changed discussion status to closed

Sign up or log in to comment