"plugins/vscode:/vscode.git/clone" did not exist on "6cfc0c906592e4fd23b0b0ed8c12b994e97dfedc"
Unverified Commit fdeb3dac authored by Jee Jee Li's avatar Jee Jee Li Committed by GitHub
Browse files

[Model] fix DeepSeek e_score_correction_bias dtype to fp32 (#23640)


Signed-off-by: default avatarJee Jee Li <pandaleefree@gmail.com>
parent d52358c1
......@@ -126,7 +126,7 @@ class DeepseekV2MoE(nn.Module):
prefix=f"{prefix}.gate")
if config.topk_method == "noaux_tc":
self.gate.e_score_correction_bias = nn.Parameter(
torch.empty(config.n_routed_experts))
torch.empty(config.n_routed_experts, dtype=torch.float32))
else:
self.gate.e_score_correction_bias = None
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment