OSError: No such device (os error 19) When Loading Model with Transformers

[jjz1011]

Token indices sequence length is longer than the specified maximum sequence length for this model (749 > 512). Running this sequence through the model will result in indexing errors Traceback (most recent call last): File "run_meta_mmd_trans.py", line 925, in base_model, base_tokenizer = load_base_model_and_tokenizer(args.base_model_name) File "run_meta_mmd_trans.py", line 531, in load_base_model_and_tokenizer base_model = transformers.AutoModelForCausalLM.from_pretrained(model_path_dit[name]) File "/root/miniconda3/envs/detectGPT/lib/python3.7/site-packages/transformers/models/auto/auto_factory.py", line 485, in from_pretrained pretrained_model_name_or_path, *model_args, config=config, hub_kwargs, kwargs File "/root/miniconda3/envs/detectGPT/lib/python3.7/site-packages/transformers/modeling_utils.py", line 2604, in from_pretrained state_dict = load_state_dict(resolved_archive_file) File "/root/miniconda3/envs/detectGPT/lib/python3.7/site-packages/transformers/modeling_utils.py", line 450, in load_state_dict with safe_open(checkpoint_file, framework="pt") as f: OSError: No such device (os error 19)

[ZSHsh98]

Thanks for your attention! There seem to be two issues with the code. Firstly, the tokenizer function missing a parameter, causes a warning. I've fixed this by adding parameters.

tokenized_data = preproc_tokenizer(long_train_real)  //old

tokenized_data = preproc_tokenizer(long_train_real, truncation=True, max_length=preproc_tokenizer.model_max_length) //now

The second issue

OSError: No such device (os error 19)

might occur if the pre-trained model isn't downloaded, leading to a failure in loading the transformers module. Please follow the steps in readme.md to download and place the pre-trained model in the correct folder.