github
/
minimind-v
mirror of https://github.com/jingyaogong/minimind-v.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[fix] dummy grad

pull/115/head
jingyaogong 2026-04-01 17:56:44 +08:00
parent 48adb0fda0
commit 28acd77d42
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
model/model_vlm.py
View File

@ -142,6 +142,7 @@ class MiniMindVLM(MiniMindForCausalLM):
hidden_states = self.model.norm(hidden_states) 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 = 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 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, :]) logits = self.lm_head(hidden_states[:, slice_indices, :])