mirror of
https://git.datalinker.icu/deepseek-ai/DeepSeek-V3.git
synced 2026-07-13 03:07:07 +08:00
fp32 gate bias
This commit is contained in:
parent
f6e34dd267
commit
4592be48c0
@ -558,7 +558,7 @@ class Gate(nn.Module):
|
|||||||
self.score_func = args.score_func
|
self.score_func = args.score_func
|
||||||
self.route_scale = args.route_scale
|
self.route_scale = args.route_scale
|
||||||
self.weight = nn.Parameter(torch.empty(args.n_routed_experts, args.dim))
|
self.weight = nn.Parameter(torch.empty(args.n_routed_experts, args.dim))
|
||||||
self.bias = nn.Parameter(torch.empty(args.n_routed_experts)) if self.dim == 7168 else None
|
self.bias = nn.Parameter(torch.empty(args.n_routed_experts, dtype=torch.float32)) if self.dim == 7168 else None
|
||||||
|
|
||||||
def forward(self, x: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
|
def forward(self, x: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||||
"""
|
"""
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user