python-3.x - 在 Python 中加载 BERT 模型时找不到 pytorch 模型
问题描述
我正在关注这篇文章以查找文本相似性。我的代码是这样的：
from sentence_transformers import SentenceTransformer
from tqdm import tqdm
from sklearn.metrics.pairwise import cosine_similarity
import numpy as np
import pandas as pd
documents = [
"Vodafone Wins ₹ 20,000 Crore Tax Arbitration Case Against Government",
"Voda Idea shares jump nearly 15% as Vodafone wins retro tax case in Hague",
"Gold prices today fall for 4th time in 5 days, down ₹6500 from last month high",
"Silver futures slip 0.36% to Rs 59,415 per kg, down over 12% this week",
"Amazon unveils drone that films inside your home. What could go wrong?",
"IPHONE 12 MINI PERFORMANCE MAY DISAPPOINT DUE TO THE APPLE B14 CHIP",
"Delhi Capitals vs Chennai Super Kings: Prithvi Shaw shines as DC beat CSK to post second consecutive win in IPL",
"French Open 2020: Rafael Nadal handed tough draw in bid for record-equaling 20th Grand Slam"
]
model = SentenceTransformer('sentence-transformers/bert-base-nli-mean-tokens')
运行上述代码时出现错误：
满的：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
~\anaconda3\envs\py3_nlp\lib\tarfile.py in nti(s)
188 s = nts(s, "ascii", "strict")
--> 189 n = int(s.strip() or "0", 8)
190 except ValueError:
ValueError: invalid literal for int() with base 8: 'ld_tenso'
During handling of the above exception, another exception occurred:
InvalidHeaderError Traceback (most recent call last)
~\anaconda3\envs\py3_nlp\lib\tarfile.py in next(self)
2298 try:
-> 2299 tarinfo = self.tarinfo.fromtarfile(self)
2300 except EOFHeaderError as e:
~\anaconda3\envs\py3_nlp\lib\tarfile.py in fromtarfile(cls, tarfile)
1092 buf = tarfile.fileobj.read(BLOCKSIZE)
-> 1093 obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors)
1094 obj.offset = tarfile.fileobj.tell() - BLOCKSIZE
~\anaconda3\envs\py3_nlp\lib\tarfile.py in frombuf(cls, buf, encoding, errors)
1034
-> 1035 chksum = nti(buf[148:156])
1036 if chksum not in calc_chksums(buf):
~\anaconda3\envs\py3_nlp\lib\tarfile.py in nti(s)
190 except ValueError:
--> 191 raise InvalidHeaderError("invalid header")
192 return n
InvalidHeaderError: invalid header
During handling of the above exception, another exception occurred:
ReadError Traceback (most recent call last)
~\anaconda3\envs\py3_nlp\lib\site-packages\torch\serialization.py in _load(f, map_location,
pickle_module, **pickle_load_args)
594 try:
--> 595 return legacy_load(f)
596 except tarfile.TarError:
~\anaconda3\envs\py3_nlp\lib\site-packages\torch\serialization.py in legacy_load(f)
505
--> 506 with closing(tarfile.open(fileobj=f, mode='r:', format=tarfile.PAX_FORMAT)) as
tar, \
507 mkdtemp() as tmpdir:
~\anaconda3\envs\py3_nlp\lib\tarfile.py in open(cls, name, mode, fileobj, bufsize, **kwargs)
1590 raise CompressionError("unknown compression type %r" % comptype)
-> 1591 return func(name, filemode, fileobj, **kwargs)
1592
~\anaconda3\envs\py3_nlp\lib\tarfile.py in taropen(cls, name, mode, fileobj, **kwargs)
1620 raise ValueError("mode must be 'r', 'a', 'w' or 'x'")
-> 1621 return cls(name, mode, fileobj, **kwargs)
1622
~\anaconda3\envs\py3_nlp\lib\tarfile.py in __init__(self, name, mode, fileobj, format, tarinfo, dereference, ignore_zeros, encoding, errors, pax_headers, debug, errorlevel, copybufsize)
1483 self.firstmember = None
-> 1484 self.firstmember = self.next()
1485
~\anaconda3\envs\py3_nlp\lib\tarfile.py in next(self)
2310 elif self.offset == 0:
-> 2311 raise ReadError(str(e))
2312 except EmptyHeaderError:
ReadError: invalid header
During handling of the above exception, another exception occurred:
RuntimeError Traceback (most recent call last)
~\anaconda3\envs\py3_nlp\lib\site-packages\transformers\modeling_utils.py in from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
1210 try:
-> 1211 state_dict = torch.load(resolved_archive_file, map_location="cpu")
1212 except Exception:
~\anaconda3\envs\py3_nlp\lib\site-packages\torch\serialization.py in load(f, map_location, pickle_module, **pickle_load_args)
425 pickle_load_args['encoding'] = 'utf-8'
--> 426 return _load(f, map_location, pickle_module, **pickle_load_args)
427 finally:
~\anaconda3\envs\py3_nlp\lib\site-packages\torch\serialization.py in _load(f, map_location, pickle_module, **pickle_load_args)
598 # .zip is used for torch.jit.save and will throw an un-pickling error here
--> 599 raise RuntimeError("{} is a zip archive (did you mean to use torch.jit.load()?)".format(f.name))
600 # if not a tarfile, reset file offset and proceed
RuntimeError: C:\Users\user1/.cache\torch\sentence_transformers\sentence-transformers_bert-base-nli-mean-tokens\pytorch_model.bin is a zip archive (did you mean to use torch.jit.load()?)
During handling of the above exception, another exception occurred:
OSError Traceback (most recent call last)
<ipython-input-3-bba56aac60aa> in <module>
----> 1 model = SentenceTransformer('sentence-transformers/bert-base-nli-mean-tokens')
~\anaconda3\envs\py3_nlp\lib\site-packages\sentence_transformers\SentenceTransformer.py in __init__(self, model_name_or_path, modules, device, cache_folder)
88
89 if os.path.exists(os.path.join(model_path, 'modules.json')): #Load as SentenceTransformer model
---> 90 modules = self._load_sbert_model(model_path)
91 else: #Load with AutoModel
92 modules = self._load_auto_model(model_path)
~\anaconda3\envs\py3_nlp\lib\site-packages\sentence_transformers\SentenceTransformer.py in _load_sbert_model(self, model_path)
820 for module_config in modules_config:
821 module_class = import_from_string(module_config['type'])
--> 822 module = module_class.load(os.path.join(model_path, module_config['path']))
823 modules[module_config['name']] = module
824
~\anaconda3\envs\py3_nlp\lib\site-packages\sentence_transformers\models\Transformer.py in load(input_path)
122 with open(sbert_config_path) as fIn:
123 config = json.load(fIn)
--> 124 return Transformer(model_name_or_path=input_path, **config)
125
126
~\anaconda3\envs\py3_nlp\lib\site-packages\sentence_transformers\models\Transformer.py in __init__(self, model_name_or_path, max_seq_length, model_args, cache_dir, tokenizer_args, do_lower_case, tokenizer_name_or_path)
27
28 config = AutoConfig.from_pretrained(model_name_or_path, **model_args, cache_dir=cache_dir)
---> 29 self.auto_model = AutoModel.from_pretrained(model_name_or_path, config=config, cache_dir=cache_dir)
30 self.tokenizer = AutoTokenizer.from_pretrained(tokenizer_name_or_path if tokenizer_name_or_path is not None else model_name_or_path, cache_dir=cache_dir, **tokenizer_args)
31
~\anaconda3\envs\py3_nlp\lib\site-packages\transformers\models\auto\auto_factory.py in from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
393 if type(config) in cls._model_mapping.keys():
394 model_class = _get_model_class(config, cls._model_mapping)
--> 395 return model_class.from_pretrained(pretrained_model_name_or_path, *model_args, config=config, **kwargs)
396 raise ValueError(
397 f"Unrecognized configuration class {config.__class__} for this kind of AutoModel: {cls.__name__}.\n"
~\anaconda3\envs\py3_nlp\lib\site-packages\transformers\modeling_utils.py in from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
1212 except Exception:
1213 raise OSError(
-> 1214 f"Unable to load weights from pytorch checkpoint file for '{pretrained_model_name_or_path}' "
1215 f"at '{resolved_archive_file}'"
1216 "If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True. "
OSError: Unable to load weights from pytorch checkpoint file for 'C:\Users\user1/.cache\torch\sentence_transformers\sentence-transformers_bert-base-nli-mean-tokens\' at 'C:\Users\user1/.cache\torch\sentence_transformers\sentence-transformers_bert-base-nli-mean-tokens\pytorch_model.bin'If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
短的：
OSError: 无法从 'C:\Users\user1/.cache\torch\sentence_transformers\sentence-transformers_bert-base-nli-mean-tokens' 的 'C:\Users\user1/.cache\ 的 pytorch 检查点文件加载权重torch\sentence_transformers\sentence-transformers_bert-base-nli-mean-tokens\pytorch_model.bin'如果您尝试从 TF 2.0 检查点加载 PyTorch 模型，请设置 from_tf=True。
我在 '.cache\torch\sentence_transformers\sentence-transformers_bert-base-nli-mean-tokens' 文件夹中有 pytorch_model.bin。
为什么我会收到此错误？
解决方案
错误的原因似乎是预训练的模型权重文件不可用或无法加载。
您可以尝试加载预训练模型权重文件：
from transformers import AutoModel
model = AutoModel.from_pretrained('sentence-transformers/bert-base-nli-mean-tokens')
参考：https ://huggingface.co/sentence-transformers/bert-base-nli-mean-tokens
此外，该模型的拥抱脸页面上写着：该模型已弃用。请不要使用它，因为它会产生低质量的句子嵌入。你可以在这里找到推荐的句子嵌入模型：SBERT.net - Pretrained Models
也许你可能想看看。
推荐阅读
- jquery - 按钮单击本地存储
- kotlin - 收到此错误“无法编译值文件”
- mysql - 在 JSON_KEYS 上加入
- reactjs - 反应重定向到移动网站
- api - SaaS 应用程序数据摄取到 DL/DWH - NFR 包括哪些内容？
- go - 如何使用从数组中获取的数据在 Golang 中创建对象对象？
- hyperledger-fabric - 不同的超级账本结构链码可以查看世界状态中的所有键/值对吗？
- pandas - Pandas 累积总和超过 1 个指数，但不是其他 3 个
- python - 我可以在dict中获取列表项吗？
- r - 与 geom_image 和 PNG 包结合使用时，geom_mark_hull 绘图不正确