diff --git a/model/model_vlm.py b/model/model_vlm.py index eb1fff5..01c2f77 100644 --- a/model/model_vlm.py +++ b/model/model_vlm.py @@ -142,6 +142,7 @@ class MiniMindVLM(MiniMindForCausalLM): hidden_states = self.model.norm(hidden_states) aux_loss = sum([l.mlp.aux_loss for l in self.model.layers if isinstance(l.mlp, MOEFeedForward)], hidden_states.new_zeros(1).squeeze()) + aux_loss = aux_loss + sum(p.sum() for p in self.vision_proj.parameters()) * 0 # dummy gradient for DDP slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep logits = self.lm_head(hidden_states[:, slice_indices, :])