Buckets:

|
download
raw
7.18 kB

AdEMAMix

AdEMAMix is a variant of the Adam optimizer.

bitsandbytes also supports paged optimizers which take advantage of CUDAs unified memory to transfer memory from the GPU to the CPU when GPU memory is exhausted.

AdEMAMix[[api-class]][[bitsandbytes.optim.AdEMAMix]]

bitsandbytes.optim.AdEMAMix[[bitsandbytes.optim.AdEMAMix]]

bitsandbytes.optim.AdEMAMix(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, optim_bits: typing.Literal[8, 32] = 32, min_8bit_size: int = 4096, is_paged: bool = False)

Source

init[[bitsandbytes.optim.AdEMAMix.init]]

__init__(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, optim_bits: typing.Literal[8, 32] = 32, min_8bit_size: int = 4096, is_paged: bool = False)

Source

AdEMAMix8bit[[bitsandbytes.optim.AdEMAMix8bit]]

bitsandbytes.optim.AdEMAMix8bit[[bitsandbytes.optim.AdEMAMix8bit]]

bitsandbytes.optim.AdEMAMix8bit(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, min_8bit_size: int = 4096, is_paged: bool = False)

Source

init[[bitsandbytes.optim.AdEMAMix8bit.init]]

__init__(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, min_8bit_size: int = 4096, is_paged: bool = False)

Source

AdEMAMix32bit[[bitsandbytes.optim.AdEMAMix32bit]]

bitsandbytes.optim.AdEMAMix32bit[[bitsandbytes.optim.AdEMAMix32bit]]

bitsandbytes.optim.AdEMAMix32bit(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, min_8bit_size: int = 4096, is_paged: bool = False)

Source

init[[bitsandbytes.optim.AdEMAMix32bit.init]]

__init__(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, min_8bit_size: int = 4096, is_paged: bool = False)

Source

PagedAdEMAMix[[bitsandbytes.optim.PagedAdEMAMix]]

bitsandbytes.optim.PagedAdEMAMix[[bitsandbytes.optim.PagedAdEMAMix]]

bitsandbytes.optim.PagedAdEMAMix(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, optim_bits: typing.Literal[8, 32] = 32, min_8bit_size: int = 4096)

Source

init[[bitsandbytes.optim.PagedAdEMAMix.init]]

__init__(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, optim_bits: typing.Literal[8, 32] = 32, min_8bit_size: int = 4096)

Source

PagedAdEMAMix8bit[[bitsandbytes.optim.PagedAdEMAMix8bit]]

bitsandbytes.optim.PagedAdEMAMix8bit[[bitsandbytes.optim.PagedAdEMAMix8bit]]

bitsandbytes.optim.PagedAdEMAMix8bit(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, min_8bit_size: int = 4096)

Source

init[[bitsandbytes.optim.PagedAdEMAMix8bit.init]]

__init__(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, min_8bit_size: int = 4096)

Source

PagedAdEMAMix32bit[[bitsandbytes.optim.PagedAdEMAMix32bit]]

bitsandbytes.optim.PagedAdEMAMix32bit[[bitsandbytes.optim.PagedAdEMAMix32bit]]

bitsandbytes.optim.PagedAdEMAMix32bit(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, min_8bit_size: int = 4096)

Source

init[[bitsandbytes.optim.PagedAdEMAMix32bit.init]]

__init__(params: collections.abc.Iterable[torch.nn.Parameter], lr: float = 0.001, betas: tuple[float, float, float] = (0.9, 0.999, 0.9999), alpha: float = 5.0, t_alpha: typing.Optional[int] = None, t_beta3: typing.Optional[int] = None, eps: float = 1e-08, weight_decay: float = 0.01, min_8bit_size: int = 4096)

Source

Xet Storage Details

Size:
7.18 kB
·
Xet hash:
d62a84a9257ca62f6687631444c9b3614199a3f14ad94507680f871523738df7

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.