Download to local file but cant run the model

[zjiang4]

from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = r"C:\Users\zjian\HuatuoGPT-o1-7B"

从本地路径加载模型和分词器

model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_path)
input_text = "How to stop a cough?"
messages = [{"role": "user", "content": input_text}]
###############
7b's problem
###############
KeyError Traceback (most recent call last)
Cell In[4], line 7
4 model_path = r"C:\Users\zjian\HuatuoGPT-o1-7B"
6 # 从本地路径加载模型和分词器
----> 7 model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype="auto", device_map="auto")
8 tokenizer = AutoTokenizer.from_pretrained(model_path)
10 input_text = "How to stop a cough?"

File ~.conda\envs\modelscope\lib\site-packages\transformers\models\auto\auto_factory.py:456, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
453 if kwargs.get("torch_dtype", None) == "auto":
454 _ = kwargs.pop("torch_dtype")
--> 456 config, kwargs = AutoConfig.from_pretrained(
457 pretrained_model_name_or_path,
458 return_unused_kwargs=True,
459 trust_remote_code=trust_remote_code,
460 **hub_kwargs,
461 **kwargs,
462 )
464 # if torch_dtype=auto was passed here, ensure to pass it on
465 if kwargs_orig.get("torch_dtype", None) == "auto":

File ~.conda\envs\modelscope\lib\site-packages\transformers\models\auto\configuration_auto.py:957, in AutoConfig.from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
955 return config_class.from_pretrained(pretrained_model_name_or_path, **kwargs)
956 elif "model_type" in config_dict:
--> 957 config_class = CONFIG_MAPPING[config_dict["model_type"]]
958 return config_class.from_dict(config_dict, **unused_kwargs)
959 else:
960 # Fallback: use pattern matching on the string.
961 # We go from longer names to shorter names to catch roberta before bert (for instance)

File ~.conda\envs\modelscope\lib\site-packages\transformers\models\auto\configuration_auto.py:671, in _LazyConfigMapping.getitem(self, key)
669 return self._extra_content[key]
670 if key not in self._mapping:
--> 671 raise KeyError(key)
672 value = self._mapping[key]
673 module_name = model_type_to_module_name(key)

KeyError: 'qwen2'

from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = r"C:\Users\zjian\HuatuoGPT-o1-8B"

从本地路径加载模型和分词器

model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_path)
input_text = "How to stop a cough?"
messages = [{"role": "user", "content": input_text}]
###############
8b's problem
###############
Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]

ValueError Traceback (most recent call last)
Cell In[5], line 7
4 model_path = r"C:\Users\zjian\HuatuoGPT-o1-8B"
6 # 从本地路径加载模型和分词器
----> 7 model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype="auto", device_map="auto")
8 tokenizer = AutoTokenizer.from_pretrained(model_path)
10 input_text = "How to stop a cough?"

File ~.conda\envs\modelscope\lib\site-packages\transformers\models\auto\auto_factory.py:484, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
482 elif type(config) in cls._model_mapping.keys():
483 model_class = _get_model_class(config, cls._model_mapping)
--> 484 return model_class.from_pretrained(
485 pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
486 )
487 raise ValueError(
488 f"Unrecognized configuration class {config.class} for this kind of AutoModel: {cls.name}.\n"
489 f"Model type should be one of {', '.join(c.name for c in cls._model_mapping.keys())}."
490 )

File ~.conda\envs\modelscope\lib\site-packages\transformers\modeling_utils.py:2881, in PreTrainedModel.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
2871 if dtype_orig is not None:
2872 torch.set_default_dtype(dtype_orig)
2874 (
2875 model,
2876 missing_keys,
2877 unexpected_keys,
2878 mismatched_keys,
2879 offload_index,
2880 error_msgs,
-> 2881 ) = cls._load_pretrained_model(
2882 model,
2883 state_dict,
2884 loaded_state_dict_keys, # XXX: rename?
2885 resolved_archive_file,
2886 pretrained_model_name_or_path,
2887 ignore_mismatched_sizes=ignore_mismatched_sizes,
2888 sharded_metadata=sharded_metadata,
2889 _fast_init=_fast_init,
2890 low_cpu_mem_usage=low_cpu_mem_usage,
2891 device_map=device_map,
2892 offload_folder=offload_folder,
2893 offload_state_dict=offload_state_dict,
2894 dtype=torch_dtype,
2895 is_quantized=(load_in_8bit or load_in_4bit),
2896 keep_in_fp32_modules=keep_in_fp32_modules,
2897 )
2899 model.is_loaded_in_4bit = load_in_4bit
2900 model.is_loaded_in_8bit = load_in_8bit

File ~.conda\envs\modelscope\lib\site-packages\transformers\modeling_utils.py:3228, in PreTrainedModel._load_pretrained_model(cls, model, state_dict, loaded_keys, resolved_archive_file, pretrained_model_name_or_path, ignore_mismatched_sizes, sharded_metadata, _fast_init, low_cpu_mem_usage, device_map, offload_folder, offload_state_dict, dtype, is_quantized, keep_in_fp32_modules)
3218 mismatched_keys += _find_mismatched_keys(
3219 state_dict,
3220 model_state_dict,
(...)
3224 ignore_mismatched_sizes,
3225 )
3227 if low_cpu_mem_usage:
-> 3228 new_error_msgs, offload_index, state_dict_index = _load_state_dict_into_meta_model(
3229 model_to_load,
3230 state_dict,
3231 loaded_keys,
3232 start_prefix,
3233 expected_keys,
3234 device_map=device_map,
3235 offload_folder=offload_folder,
3236 offload_index=offload_index,
3237 state_dict_folder=state_dict_folder,
3238 state_dict_index=state_dict_index,
3239 dtype=dtype,
3240 is_quantized=is_quantized,
3241 is_safetensors=is_safetensors,
3242 keep_in_fp32_modules=keep_in_fp32_modules,
3243 )
3244 error_msgs += new_error_msgs
3245 else:

File ~.conda\envs\modelscope\lib\site-packages\transformers\modeling_utils.py:720, in _load_state_dict_into_meta_model(model, state_dict, loaded_state_dict_keys, start_prefix, expected_keys, device_map, offload_folder, offload_index, state_dict_folder, state_dict_index, dtype, is_quantized, is_safetensors, keep_in_fp32_modules)
717 state_dict_index = offload_weight(param, param_name, state_dict_folder, state_dict_index)
718 elif not is_quantized:
719 # For backward compatibility with older versions of accelerate
--> 720 set_module_tensor_to_device(model, param_name, param_device, **set_module_kwargs)
721 else:
722 if param.dtype == torch.int8 and param_name.replace("weight", "SCB") in state_dict.keys():

File ~.conda\envs\modelscope\lib\site-packages\accelerate\utils\modeling.py:285, in set_module_tensor_to_device(module, tensor_name, device, value, dtype, fp16_statistics)
283 if value is not None:
284 if old_value.shape != value.shape:
--> 285 raise ValueError(
286 f'Trying to set a tensor of shape {value.shape} in "{tensor_name}" (which has shape {old_value.shape}), this look incorrect.'
287 )
289 if dtype is None:
290 # For compatibility with PyTorch load_state_dict which converts state dict dtype to existing dtype in model
291 value = value.to(old_value.dtype)

ValueError: Trying to set a tensor of shape torch.Size([1024, 4096]) in "weight" (which has shape torch.Size([4096, 4096])), this look incorrect.