Godlikemandyy
Godlikemandyy
When I read a pdf file, I found page.extract_text() to get the texts what has a lot of dislocation, eg: the image of pdf is following: but I get the...
What do I need to do if I want to achieve this！ Thank you！
文件编码有问题
你好，我试着跑了一下bert_corrector.py代码，发现文件编码的错误，具体如下： Traceback (most recent call last): File "D:/soft/bert_for_corrector/bert_corrector.py", line 73, in d = BertCorrector() File "D:/soft/bert_for_corrector/bert_corrector.py", line 23, in __init__ tokenizer=bert_model_dir) File "D:\Anaconda3\Lib\site-packages\transformers\pipelines.py", line 2727, in pipeline framework = framework...
@jsvine I have a new situation. I solved the previous problem by adjusting y_tolerance, but I encountered the following problem with the new document. The document format is as follows:...
大佬，你好： 尝试跑了一下elt_span_transformers发现报了一些错误： 2021-01-26 14:49:24,295 - transformers.tokenization_utils - INFO - Model name 'transformer_model_path' not found in model shortcut name list (bert-base-uncased, bert-large-uncased, ber t-base-cased, bert-large-cased, bert-base-multilingual-uncased, bert-base-multilingual-cased, bert-base-chinese, bert-base-german-cased, bert-large-uncased-whole-word-masking, bert-lar...
### Is your feature request related to a problem? Please describe. 一共准备了300多条数据，二八分为测试集和训练集；微调用的参数和项目一样； 数据集准备是按照下面的方式准备的问答对，没有涉及多轮问答，history设置的是空list： ### Solutions 测试了一下微调后的效果，发现有点不太说人话，而且不同的问题重复回答同一个答案，并且感觉丧失了一些通用领域问题的回答能力： 想了解一下，出现这种现象是什么原因造成的？ 如果微调用的数据集使用多轮对话的，会避免或者较少这种问题吗？ 或者是不是其他微调方法会更好一些呢，比如说lora，或者全参数finetune？ ### Additional context 顺便想了解一些微调后evaluate结束后的指标值是啥意思，能不能给出一些指标的详细介绍和取值范围，要不然不太清楚如何评价微调后的模型效果好不好。 期待解惑，坐等！！！
I want to achieve a small function, that is, the formula and equation can achieve step by step calculation.But I looked through the documentation and didn't see any code examples,...
直接运行命令`python convert.py`有以下错误： TypeError: forward() got an unexpected keyword argument 'pos_ids' 请问这是什么原因造成的？