pub struct KdaDims {
pub hidden: usize,
pub heads: usize,
pub head_dim: usize,
pub tokens: usize,
}Expand description
KDA geometry. Production is hidden 4096 / heads 64 / head_dim 128; the low-rank width for
both f_a/f_b and g_a/g_b equals head_dim.
Fields§
§heads: usize§head_dim: usize§tokens: usizeTrait Implementations§
Auto Trait Implementations§
impl Freeze for KdaDims
impl RefUnwindSafe for KdaDims
impl Send for KdaDims
impl Sync for KdaDims
impl Unpin for KdaDims
impl UnwindSafe for KdaDims
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more