shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = emb.chunk(6, dim=1) ValueError: not enough values to unpack (expected 6, got 4)

[LianShuaiLong]

To save GPU memory during training, I pre-extracted the text embeddings. During the training process, I did not load the text encoders and directly used the embeddings for training. However, I encountered the following error:

shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = emb.chunk(6, dim=1)
ValueError: not enough values to unpack (expected 6, got 4)

Here is my feature extraction script and the modified training script. Could someone kindly help me identify where the issue might be?

[LianShuaiLong]

[
tmp.zip
](url)

[a-r-r-o-w]

Could you share your code in a public repository instead of a zip file? Which model are you trying to train?

[LianShuaiLong]

Could you share your code in a public repository instead of a zip file? Which model are you trying to train?

flux1-dev,These are the scripts for extracting text embeddings and initiating LoRA training. No other scripts are involved in these two processes.