colab doesn't work

[chuangzhidan]

model = get_model(model_name, peft_path)
when it exec to this line of code , i get the following error.
i bet it has sth to do with the model's path,so ,how do i fix it?

Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Loading model...THUDM/chatglm-6b lora:silk-road/luotuo-qa-lora-0.1
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ in <cell line: 1>:1 │
│ │
│ /content/luotuo_qa/app/infer.py:19 in get_model │
│ │
│ 16 │ from transformers import AutoModel │
│ 17 │ import torch │
│ 18 │ torch.set_default_tensor_type(torch.cuda.HalfTensor) │
│ ❱ 19 │ model = AutoModel.from_pretrained(model_name, trust_remote_code=True, device_map='au │
│ 20 │ if peft_path is not None and peft_path != "": │
│ 21 │ │ model = PeftModel.from_pretrained(model, peft_path) │
│ 22 │ return model │
│ │
│ /usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py:462 in │
│ from_pretrained │
│ │
│ 459 │ │ │ │ ) │
│ 460 │ │ │ class_ref = config.auto_map[cls.name] │
│ 461 │ │ │ module_file, class_name = class_ref.split(".") │
│ ❱ 462 │ │ │ model_class = get_class_from_dynamic_module( │
│ 463 │ │ │ │ pretrained_model_name_or_path, module_file + ".py", class_name, **hub_kw │
│ 464 │ │ │ ) │
│ 465 │ │ │ model_class.register_for_auto_class(cls.name) │
│ │
│ /usr/local/lib/python3.10/dist-packages/transformers/dynamic_module_utils.py:388 in │
│ get_class_from_dynamic_module │
│ │
│ 385 │ cls = get_class_from_dynamic_module("sgugger/my-bert-model", "modeling.py", "MyBertM │
│ 386 │ ```""" │