text encoder lora unloaded

[DarkViewAI]

Trained a model/concept style on two h100 gpus experimenting with the text encoder,

the lora works on comfyui but it says

lora_te1.text_model.encoder.layers.8.mlp.fc1.lora_a.weight lora_te1.text_model.encoder.layers.7.mlp.fc1.lora_B.weight

the images work fine

when i try it on forge it unloads it and just inputs a base image, my lora doesn't work.