Qwen

/

Qwen3-Reranker-0.6B

like 350

Follow

Qwen 84.6k

TypeError Traceback (most recent call last)
Cell In[3], line 5
2 from transformers import AutoTokenizer, AutoModelForCausalLM
4 tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Reranker-0.6B", cache_dir="/workspace/raw_model/")
----> 5 model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Reranker-0.6B", cache_dir="/workspace/raw_model/")

File /usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py:571, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
569 if model_class.config_class == config.sub_configs.get("text_config", None):
570 config = config.get_text_config()
--> 571 return model_class.from_pretrained(
572 pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
573 )
574 raise ValueError(
575 f"Unrecognized configuration class {config.class} for this kind of AutoModel: {cls.name}.\n"
576 f"Model type should be one of {', '.join(c.name for c in cls._model_mapping.keys())}."
577 )

File /usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py:309, in restore_default_torch_dtype.._wrapper(*args, **kwargs)
307 old_dtype = torch.get_default_dtype()
308 try:
--> 309 return func(*args, **kwargs)
310 finally:
311 torch.set_default_dtype(old_dtype)

File /usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py:4508, in PreTrainedModel.from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, weights_only, *model_args, **kwargs)
4499 config = cls._autoset_attn_implementation(
4500 config,
4501 use_flash_attention_2=use_flash_attention_2,
4502 torch_dtype=torch_dtype,
4503 device_map=device_map,
4504 )
4506 with ContextManagers(model_init_context):
4507 # Let's make sure we don't run the init function of buffer modules
-> 4508 model = cls(config, *model_args, **model_kwargs)
4510 # Make sure to tie the weights correctly
4511 model.tie_weights()

File /usr/local/lib/python3.10/dist-packages/transformers/models/qwen3/modeling_qwen3.py:660, in Qwen3ForCausalLM.init(self, config)
658 def init(self, config):
659 super().init(config)
--> 660 self.model = Qwen3Model(config)
661 self.vocab_size = config.vocab_size
662 self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)

File /usr/local/lib/python3.10/dist-packages/transformers/models/qwen3/modeling_qwen3.py:389, in Qwen3Model.init(self, config)
386 self.gradient_checkpointing = False
388 # Initialize weights and apply final processing
--> 389 self.post_init()

File /usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py:1969, in PreTrainedModel.post_init(self)
1967 if self._tp_plan is not None and is_torch_greater_or_equal("2.3"):
1968 for _, v in self._tp_plan.items():
-> 1969 if v not in ALL_PARALLEL_STYLES:
1970 raise ValueError(
1971 f"Unsupported tensor parallel style {v}. Supported styles are {ALL_PARALLEL_STYLES}"
1972 )

TypeError: argument of type 'NoneType' is not iterable