Jingyuan Wen

您好！ 关于CSLDCP数据集，您的Readme和论文中提到的数据量都为train:val:test = 536:536:1784 然而下载后，发现train_few_all: dev_few_all: test_public = 2036:2068:1784 请问是版本不同吗？这两版数据有什么区别吗？ 谢谢！

使用RoBERTa-large无法复现P-Tuning结果

11

您好，很感谢您的工作！ 我在tnews数据集上复现时p-tuning，使用RoBERTa-wwm-ext可以得到与论文相近的结果，但是改成RoBERTa-wwm-ext-large后结果很差，仅比random的结果好一点。 我更换模型时只更改了预训练模型的路径 ``` base_model_path = './chinese_roberta_wwm_large_ext_L-24_H-1024_A-16' config_path = base_model_path+'bert_config.json' checkpoint_path = base_model_path+'bert_model.ckpt' dict_path = base_model_path+'vocab.txt' ``` 我并没有发现其他需要改动的地方，请问这样有问题吗？我尝试调整了学习率等超参数，但效果依然不佳

"TypeError: can only concatenate str (not "float") to str" while training with transformer_nsc

2

Hi @ruotianluo , sorry to disturb you, but I got error as the title when I try to train a transformer model using nsc. My command is `python tools/train.py --cfg...

您好，没有看到inews数据集的下载链接

[BUG] <title>batch_infer报错：'tuple' object has no attribute 'dtype'

2

### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答？ | Is there an...