yongzhuo / pytorch-nlu Goto Github PK

大佬跪求MiningZhiDaoQACorpus这个数据集求的共享链接，原链接失效了
万分感谢

self.pretrain_model = pretrained_model(self.pretrained_config) # 推理时候只需要加载超参数, 不需要预训练模型的权重

预训练模型是bert-tiny，加载用的AutotModel，不是BertModel
在tcGraph.py的这行报错，报错如下

OSError: AutoModel is designed to be instantiated using the AutoModel.from_pretrained(pretrained_model_name_or_path) or AutoModel.from_config(config) methods.

这两个类变量在哪定义的？跑代码时报错！

进行文本多标签分类，数据有90多万，txt文件有不到200m，但是读取数据集占用的内存太多了，不知道是不是bug还是本来就这样，机子32g的内存都不够读取四分之一的数据，

比如这些预训练模型去哪里下载。

首先感谢作者的贡献，特别是中文NER的loss汇总实现对我帮助很大

您好，我想问下这里是否包含了FLAT的相对位置矩阵的实现呢，可能是我看漏了

The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'BertTokenizer'.
The class this function is called from is 'AlbertTokenizer'.
Traceback (most recent call last):
File "/home/efsz/localCode/Pytorch-NLU/test/tc/tet_tc_base_multi_label.py", line 73, in
lc.process()
File "/home/efsz/localCode/Pytorch-NLU/pytorch_nlu/pytorch_textclassification/tcRun.py", line 32, in process
self.corpus = Corpus(self.config, self.logger)
File "/home/efsz/localCode/Pytorch-NLU/pytorch_nlu/pytorch_textclassification/tcData.py", line 25, in init
self.tokenizer = self.load_tokenizer(self.config)
File "/home/efsz/localCode/Pytorch-NLU/pytorch_nlu/pytorch_textclassification/tcData.py", line 206, in load_tokenizer
tokenizer = PRETRAINED_MODEL_CLASSES[config.model_type][1].from_pretrained(config.pretrained_model_name_or_path)
File "/home/efsz/anaconda3/envs/nlu/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1854, in from_pretrained
return cls._from_pretrained(
File "/home/efsz/anaconda3/envs/nlu/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2017, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/home/efsz/anaconda3/envs/nlu/lib/python3.10/site-packages/transformers/models/albert/tokenization_albert.py", line 183, in init
self.sp_model.Load(vocab_file)
File "/home/efsz/anaconda3/envs/nlu/lib/python3.10/site-packages/sentencepiece/init.py", line 905, in Load
return self.LoadFromFile(model_file)
File "/home/efsz/anaconda3/envs/nlu/lib/python3.10/site-packages/sentencepiece/init.py", line 310, in LoadFromFile
return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
TypeError: not a string

其他模型好像没问题，但是albert的tokenizer加载会报这个错

以给定的school为例，测试集一共有132条，其中多标签的12条，单标签的120条，最后support和为120. 我单步调试看了一下，多标签的样本输入时one hot向量是全零的，想问一下这一步什么原理？