Hello there,
This is regarding L3. I was trying to run the similar setup from ide.
I have downloaded the Qwen( as mentioned in the course structure) model it the local file system.
Created the code and applied all the checks for example version of the transformer, trusting remote code and local files only.
I checked the transformer library version and its
Transformers version: 4.52.4
However its giving me an error.Its able to load the Tokenizer, however failed in the loading of the model.
File "\model_train\try_sft_train.py", line 62, in load_model_and_tokenizer
ret_model = AutoModelForCausalLM.from_pretrained(model_id , trust_remote_code=True, local_files_only=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "\.venv\Lib\site-packages\transformers\models\auto\auto_factory.py", line 571, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "\.venv\Lib\site-packages\transformers\modeling_utils.py", line 309, in _wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "\.venv\Lib\site-packages\transformers\modeling_utils.py", line 4508, in from_pretrained
model = cls(config, *model_args, **model_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "\.venv\Lib\site-packages\transformers\models\qwen3\modeling_qwen3.py", line 660, in __init__
self.model = Qwen3Model(config)
^^^^^^^^^^^^^^^^^^
File "\.venv\Lib\site-packages\transformers\models\qwen3\modeling_qwen3.py", line 389, in __init__
self.post_init()
File "\.venv\Lib\site-packages\transformers\modeling_utils.py", line 1969, in post_init
if v not in ALL_PARALLEL_STYLES:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: argument of type 'NoneType' is not iterable
PS: I have trimmed down the path since it contains sensitive data.