d_model (C)
Also written: d_model, C, width, model width
The size of the vectors that flow through the model, also called its width. In code it is often written C; GPT-3's is 12,288.
Also written: d_model, C, width, model width
The size of the vectors that flow through the model, also called its width. In code it is often written C; GPT-3's is 12,288.