From 515f261824bc7aad15aa4770a5beaa1f1b9d69bc Mon Sep 17 00:00:00 2001 From: songsenand Date: Sun, 15 Feb 2026 00:25:38 +0800 Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E5=A4=8D=E6=A8=A1=E5=9E=8B=E5=8A=A0?= =?UTF-8?q?=E8=BD=BD=E6=96=B9=E6=B3=95=EF=BC=8C=E4=BD=BF=E7=94=A8=E6=AD=A3?= =?UTF-8?q?=E7=A1=AE=E7=9A=84=E5=AE=9E=E4=BE=8B=E6=96=B9=E6=B3=95=E5=8A=A0?= =?UTF-8?q?=E8=BD=BD=E7=8A=B6=E6=80=81=E5=AD=97=E5=85=B8?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- src/trainer/model_with_neck.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/trainer/model_with_neck.py b/src/trainer/model_with_neck.py index ceec383..2f36f39 100644 --- a/src/trainer/model_with_neck.py +++ b/src/trainer/model_with_neck.py @@ -585,7 +585,7 @@ class MoEModel(nn.Module): state_dict = torch.load( state_dict_path, weights_only=True, map_location=self.device ) - self.model.load_state_dict(state_dict) + self.load_state_dict(state_dict) def load_from_pretrained_base_model( self,