Data

Tools

Indexes

Applications

Experiments

Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / Morizeyao/GPT2-Chinese issues and pull requests

#296 - 预训练模型的名字什么鬼

Issue - State: open - Opened by AlisonDexter over 1 year ago

#295 - json不对，无法训练

Issue - State: open - Opened by LeoGoat2004 over 1 year ago

#293 - 求助求助

Issue - State: open - Opened by 3215838277 over 1 year ago

#266 - 古诗和古文模型的训练数据哪里可以下载？

Issue - State: open - Opened by superhg over 2 years ago - 1 comment

#102 - 可以用这个写喜羊羊和懒羊羊的爱情故事吗

Issue - State: closed - Opened by taroorat almost 6 years ago - 1 comment

#101 - fix gradient accumulation bug

Pull Request - State: closed - Opened by lioyou almost 6 years ago - 2 comments

#99 - 用金庸15部小说训练

Issue - State: open - Opened by yangjianxin1 almost 6 years ago - 12 comments

#98 - 生成文本如何提高多样性

Issue - State: closed - Opened by dkicenan almost 6 years ago - 5 comments

#97 - train.json这么填，是有问题的。正确的格式是？

Issue - State: closed - Opened by jason5675 almost 6 years ago - 4 comments

#95 - 单GPU训练应该该哪些参数

Issue - State: closed - Opened by lucasjinreal almost 6 years ago - 10 comments

#94 - 为什么train_simple也是读取json的逻辑？

Issue - State: closed - Opened by lucasjinreal almost 6 years ago - 3 comments

#93 - Undefined name 'encoder_path' in bpe_tokenizer.py

Issue - State: closed - Opened by cclauss almost 6 years ago - 1 comment

#92 - train的时候为啥不用model(input_ids, lm_labels)，而用forward函数呢？

Issue - State: closed - Opened by jason5675 almost 6 years ago - 2 comments

#91 - 认为这段代码有重大bug

Issue - State: closed - Opened by jason5675 almost 6 years ago - 6 comments

#90 - Create vocab.bpe !

Issue - State: closed - Opened by ngocpham97 almost 6 years ago - 4 comments

#89 - readme里说可以用BPE tokenizer，但是其实目前并不支持啊。

Issue - State: closed - Opened by jason5675 almost 6 years ago - 6 comments

#88 - 生成的文本都是乱码

Issue - State: open - Opened by jason5675 almost 6 years ago - 18 comments

#85 - 生成文本出现编码问题

Issue - State: closed - Opened by ShengXiaoXiao almost 6 years ago - 5 comments

#84 - Fine tuning on custom language

Issue - State: closed - Opened by Radeeswar almost 6 years ago - 2 comments

#83 - Can I use it for chatbot?

Issue - State: closed - Opened by Monica9502 almost 6 years ago - 1 comment

#82 - 文学散文训练模型分享，同时添加模型共享列表

Pull Request - State: closed - Opened by hughqiu almost 6 years ago

#79 - 能否稍微补充一下train.json的数据范例，试了几种格式都不太对

Issue - State: closed - Opened by lileieiei almost 6 years ago - 1 comment

#78 - 微信交流群

Issue - State: closed - Opened by Morizeyao almost 6 years ago - 21 comments

#77 - 训练损失值得问题

Issue - State: closed - Opened by DarylLei almost 6 years ago - 7 comments

#76 - 下载的斗破语料生成为什么会是乱码呢

Issue - State: open - Opened by cuyoo almost 6 years ago - 15 comments

#75 - 训练的时候总是出现这个issue

Issue - State: closed - Opened by JiaLei123 almost 6 years ago - 2 comments

#74 - 請問data/tokenized的文件去哪取得

Issue - State: closed - Opened by cbt36594 almost 6 years ago - 3 comments

#73 - 如何做限定体裁的生成

Issue - State: closed - Opened by MrRace almost 6 years ago - 1 comment

#72 - 训练数据处理的疑问

Issue - State: closed - Opened by caishiqing almost 6 years ago - 6 comments

#71 - 生成效果的疑问

Issue - State: closed - Opened by caishiqing almost 6 years ago - 4 comments

#70 - running_loss的计算以及清空方式或存在重大Bug?

Issue - State: closed - Opened by xinfeng1i almost 6 years ago - 3 comments

#69 - 对 total_steps 的估算?

Issue - State: closed - Opened by xinfeng1i almost 6 years ago - 1 comment

#68 - 关于在训练文本里添加标签的想法

Issue - State: closed - Opened by hughqiu almost 6 years ago - 3 comments

#67 - 训练好的模型能提供吗

Issue - State: closed - Opened by duguiming111 almost 6 years ago - 1 comment

#66 - 句子的困惑度/得分计算？

Issue - State: closed - Opened by xinfeng1i almost 6 years ago - 11 comments

#65 - 训练时候报错RuntimeError: CUDA error: device-side assert triggered

Issue - State: closed - Opened by yxt132 almost 6 years ago - 28 comments

#63 - 文章摘要生成

Issue - State: closed - Opened by maozezhong almost 6 years ago - 5 comments

#62 - 模型共享

Issue - State: closed - Opened by chunpingji almost 6 years ago - 1 comment

#61 - generate.py中参数batch_size的作用

Issue - State: closed - Opened by lioyou almost 6 years ago - 4 comments

#60 - gradient_accumulation及warmup_steps参数问题

Issue - State: closed - Opened by lioyou almost 6 years ago - 3 comments

#59 - 新增金庸武俠小說生成樣例、介紹文章及 Colab 筆記本

Pull Request - State: closed - Opened by leemengtw almost 6 years ago - 2 comments

#58 - Improving data processing way to avoid discard data

Pull Request - State: closed - Opened by lioyou almost 6 years ago

#57 - 改进数据处理方式避免丢失数据

Pull Request - State: closed - Opened by lioyou almost 6 years ago - 1 comment

#56 - 参数 n_ctx

Issue - State: closed - Opened by haif-liu almost 6 years ago - 17 comments

#55 - 训练数据丢失问题

Issue - State: closed - Opened by lioyou almost 6 years ago - 9 comments

#54 - BPE 使用

Issue - State: closed - Opened by NiceMartin almost 6 years ago - 9 comments

#53 - Bugfix: close the file pointer when finishing writing

Pull Request - State: closed - Opened by xinfeng1i almost 6 years ago

#52 - Bug: 文件指针没有被关闭

Issue - State: closed - Opened by xinfeng1i almost 6 years ago - 2 comments

#50 - 。

Issue - State: closed - Opened by Cyvadra almost 6 years ago

#47 - 运行train.py 的时候报错 module 'tensorflow.io' has no attribute 'gfile'

Issue - State: closed - Opened by JiaLei123 about 6 years ago - 3 comments

#46 - add fast generate

Pull Request - State: closed - Opened by fengzuo97 about 6 years ago - 1 comment

#45 - 生成的速度太慢了，能否加一个生成的batch_size大于1的功能

Issue - State: closed - Opened by huosu about 6 years ago - 6 comments

#44 - fix mismatched parameter name

Pull Request - State: closed - Opened by leemengtw about 6 years ago - 1 comment

#43 - RuntimeError: Creating MTGP constants failed.

Issue - State: open - Opened by leemengtw about 6 years ago - 14 comments

#42 - 句子过长导致的索引错误（Too long a sentence leads to an index error）

Issue - State: closed - Opened by lioyou about 6 years ago - 3 comments

#41 - 增加sentencepiece支持

Pull Request - State: closed - Opened by kangzhonghua about 6 years ago - 1 comment

#40 - 添加自定义文件类型及数据源支持

Pull Request - State: closed - Opened by lioyou about 6 years ago - 1 comment

#39 - 用CPU执行train_single训练，报这个错误RuntimeError: index out of range

Issue - State: closed - Opened by leedaga about 6 years ago - 2 comments

#38 - argparse中参数gradient_accumulation类型错误

Issue - State: closed - Opened by xinfeng1i about 6 years ago - 3 comments

#37 - where can download the trained model

Issue - State: closed - Opened by molsheim about 6 years ago - 1 comment

#36 - 生成的古诗中包含大量UNK

Issue - State: closed - Opened by lijun20 about 6 years ago - 2 comments

#35 - Fail to run train_single

Issue - State: closed - Opened by diansheng about 6 years ago - 1 comment

#34 - Undefined name 'running_loss' in ./train_single.py

Issue - State: closed - Opened by cclauss about 6 years ago - 1 comment

#33 - Word branch

Pull Request - State: closed - Opened by fengzuo97 about 6 years ago - 4 comments

#32 - 多gpu混合精度训练的问题

Issue - State: closed - Opened by fengzuo97 about 6 years ago - 5 comments

#29 - 请问能否支持非续写模式的generate?

Issue - State: closed - Opened by lexmen318 about 6 years ago - 6 comments

#28 - nothing

Issue - State: closed - Opened by ashora about 6 years ago - 1 comment

#27 - 可否有监督

Issue - State: closed - Opened by WeiliangGuo about 6 years ago - 1 comment

#26 - 是否保存optimizer的参数？

Issue - State: closed - Opened by fengzuo97 about 6 years ago - 1 comment

#25 - cannot import name 'clean_up_tokenization'

Issue - State: closed - Opened by leemengtw about 6 years ago - 6 comments

#24 - 训练成果分享与一点提问

Issue - State: closed - Opened by chiangandy about 6 years ago - 17 comments

#23 - #分词训练格式

Issue - State: closed - Opened by kangkang61 about 6 years ago - 4 comments

#22 - 训练数据格式问题

Issue - State: closed - Opened by huaxiaohua about 6 years ago - 3 comments

#21 - 环境使用内存的问题

Issue - State: closed - Opened by chiangandy about 6 years ago - 4 comments

#20 - 软件包安装问题

Issue - State: closed - Opened by chiangandy about 6 years ago - 2 comments

#19 - #loss每个num_piece会先增加再减

Issue - State: closed - Opened by cyl250 about 6 years ago - 1 comment

#18 - 请问词表有预训练权重么

Issue - State: closed - Opened by ZhaoyueSun about 6 years ago - 2 comments

#17 - #局部收敛问题

Issue - State: closed - Opened by cyl250 about 6 years ago - 6 comments

#16 - 求教一般训练几个epoch？

Issue - State: closed - Opened by ZhaoyueSun about 6 years ago - 3 comments

#15 - 训练的loss或者ppl？使用分字和分词的效果对比？

Issue - State: closed - Opened by fengzuo97 about 6 years ago - 8 comments

#14 - 硬件

Issue - State: closed - Opened by nlpofwhat about 6 years ago - 2 comments

#13 - add some samples with fixed genre

Pull Request - State: closed - Opened by JamesHujy about 6 years ago

#12 - 请教只训练语言模型

Issue - State: closed - Opened by kangkang61 about 6 years ago - 1 comment

#11 - 请问是从预训练模型开始训练的吗？

Issue - State: closed - Opened by Dongfeng-He about 6 years ago - 2 comments

#10 - poem generation samples

Pull Request - State: closed - Opened by JamesHujy about 6 years ago

#9 - 请教体育新闻的语料数量

Issue - State: closed - Opened by chiangandy about 6 years ago - 1 comment

#8 - 正体中文支援的问题

Issue - State: closed - Opened by chiangandy about 6 years ago - 1 comment

#7 - 训练好的模型移至CPU上执行

Issue - State: closed - Opened by chiangandy about 6 years ago - 1 comment