Skip to content

Issues: 920232796/bert_seq2seq

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

49 Open 18 Closed
49 Open 18 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

关于分词示例roberta_participle_CRF_train.py
#71 opened Nov 20, 2023 by Turskey
数据集分享
#70 opened May 12, 2023 by zhangzai666
我从新改变了vocab.txt的大小，在加载预训练模型的时候出现维度不匹配，请问应该怎么解决了？我发现代码里面有个keep_tokens,似乎可以解决，但我不知道keep_tokens改如何设置。
#68 opened Mar 22, 2023 by panbo-bridge
多卡训练失败，目前有4个gpu，但使用的时候一直显示用的cuda0，指定其他cuda也不生效
#66 opened Nov 30, 2022 by GUORUIWANG
关于UniLM
#65 opened Oct 24, 2022 by cppww
1
关于细粒度NER数据集
#64 opened Oct 8, 2022 by the9527001
自動摘要 fine tune
#63 opened Aug 30, 2022 by frankShih
1
您好 请问在simbert模型里面 seq2seq的loss比similarity的loss大的多是正常的吗？
#61 opened Jul 10, 2022 by EddieChen324
3
你好，我想问一下，关于gpt文章写作的数据集应该是什么样的格式，是一小段标题作为输入，文章作为输出么？
#58 opened May 15, 2022 by viego1999
5
请问在做标题生成的时候支持point_net对应的copy机制吗？
#57 opened Apr 18, 2022 by chenzelong
1
如何能联系到您呢？qq群加不进去，有关于epoch和bart做seq2seq方面的问题想请教一下> > 您好 在不断降低学习率之后loss还是卡在原来的位置，请问如何能与您取得联系？
#56 opened Apr 15, 2022 by chenzelong
5
unilm多少epoch收敛比较好？
#55 opened Apr 15, 2022 by chenzelong
1
请问bart做标题生成怎么跑起来？
#54 opened Apr 15, 2022 by chenzelong
4
您好，我想添加一些我自己的数据集做fine-tune，请问应该怎么做呢
#52 opened Mar 14, 2022 by pangsg
1
roberta_auto_title_train.py
#50 opened Feb 11, 2022 by lishuzhen97
4
1. 关于多卡训练支持建议。2. 关于tokenizer的pre_train建议。3. 关于外露模型配置API的建议。
#49 opened Dec 10, 2021 by PolarisRisingWar
1
simbert_model.py文件中的117行
#48 opened Dec 7, 2021 by singaln
5
模型加载输出问题
#47 opened Dec 1, 2021 by yang41690104
5
如何使用问题？
#46 opened Nov 25, 2021 by Jockz
1
关于数据集问题
#45 opened Nov 17, 2021 by XingyuZhu-Pamela
2
关于医学代码的问题
#43 opened Oct 7, 2021 by cc846049716
16
三元组信息抽取中随机抽取object，最终只用到了object开始、结束字符对应的编码用于predict、subject预测，这样是否合理呢
#42 opened Sep 15, 2021 by jackjqli
1
粗粒度NER-tokenizer问题
#41 opened Aug 1, 2021 by NiceMartin
1
代码问题 multi-head attention 中的 extended_attention_mask
#39 opened Jul 17, 2021 by NiceMartin
4
关于标题分类的问题
#38 opened Jul 15, 2021 by Evialzhang
1
ProTip! no:milestone will show everything without a milestone.