Alison
Alison
ile "d:\Bert_pre\GPT_2\GPT2-Chinese-old_gpt_2_chinese_before_2021_4_22\GPT2-Chinese-old_gpt_2_chinese_before_2021_4_22\tokenizations\tokenization_bert.py", line 131, in __init__ "model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`".format(vocab_file)) ValueError: Can't find a vocabulary file at path 'cache/vocab_small.txt'. To load the vocabulary from a Google pretrained model use...
训练模型问题
是不是用新的数据集,通过train.py就能训练出来新的模型
你好,请问你训练一个新语言识别模型时,这个train_text_language.txt中的标签是如何给值的,是给zh吗?还是可以自定义一个新的呢?