size mismatch on adapter model

[chris-aeviator]

model = AutoModelForCausalLM.from_pretrained("malteos/bloom-6b4-clp-german PeftModel.from_pretrained(model, "snipaid/snip-igel-500-v2")
!pip install -q transformers datasets accelerate bitsandbytes sentencepiece
!pip install -q git+https://github.com/huggingface/peft.gi

`
size mismatch for base_model.model.transformer.h.3.self_attention.query_key_value.lora_B.default.weight:
copying a param with shape torch.Size([8192, 8, 1]) from checkpoint, the shape in current model is
torch.Size([12288, 8]).
``