Closed mutetea closed 9 months ago
Hi @mutetea, sorry for the delayed relay.
For LlamaForSequenceClassification
, we use the official implementation. The classification layer with the name classifier
is automatically added to the trainable parameters in PEFT, you can check this: https://github.com/huggingface/peft/blob/main/src/peft/peft_model.py#L788-L791
For llama_seq_clf,it seems you just use LlamaForSeq Classification,which use a new linear head to substitute the original head.
I don't think LoRA train this layer,why this is not an issue?