Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / Morizeyao/GPT2-Chinese issues and pull requests
#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 5 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 5 years ago
- 1 comment
#101 - fix gradient accumulation bug
Pull Request -
State: closed - Opened by lioyou almost 5 years ago
- 2 comments
#101 - fix gradient accumulation bug
Pull Request -
State: closed - Opened by lioyou almost 5 years ago
- 2 comments
#100 - 就突然想问一下,为啥不把model的模型写到gpu内存里????
Issue -
State: closed - Opened by qiyuanshijie almost 5 years ago
#100 - 就突然想问一下,为啥不把model的模型写到gpu内存里????
Issue -
State: closed - Opened by qiyuanshijie almost 5 years ago
#99 - 用金庸15部小说训练
Issue -
State: open - Opened by yangjianxin1 about 5 years ago
- 12 comments
#99 - 用金庸15部小说训练
Issue -
State: open - Opened by yangjianxin1 about 5 years ago
- 12 comments
#98 - 生成文本如何提高多样性
Issue -
State: closed - Opened by dkicenan about 5 years ago
- 5 comments
#98 - 生成文本如何提高多样性
Issue -
State: closed - Opened by dkicenan about 5 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 about 5 years ago
- 4 comments
#97 - train.json这么填,是有问题的。正确的格式是?
Issue -
State: closed - Opened by jason5675 about 5 years ago
- 4 comments
#96 - 怎么老是报gpu内存溢出。训练几百步后就报。训练预料是一行一句话,总共也就50w行。
Issue -
State: closed - Opened by jason5675 about 5 years ago
- 1 comment
#96 - 怎么老是报gpu内存溢出。训练几百步后就报。训练预料是一行一句话,总共也就50w行。
Issue -
State: closed - Opened by jason5675 about 5 years ago
- 1 comment
#95 - 单GPU训练应该该哪些参数
Issue -
State: closed - Opened by lucasjinreal about 5 years ago
- 10 comments
#95 - 单GPU训练应该该哪些参数
Issue -
State: closed - Opened by lucasjinreal about 5 years ago
- 10 comments
#94 - 为什么train_simple也是读取json的逻辑?
Issue -
State: closed - Opened by lucasjinreal about 5 years ago
- 3 comments
#93 - Undefined name 'encoder_path' in bpe_tokenizer.py
Issue -
State: closed - Opened by cclauss about 5 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 about 5 years ago
- 2 comments
#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 about 5 years ago
- 2 comments
#91 - 认为这段代码有重大bug
Issue -
State: closed - Opened by jason5675 about 5 years ago
- 6 comments
#91 - 认为这段代码有重大bug
Issue -
State: closed - Opened by jason5675 about 5 years ago
- 6 comments
#90 - Create vocab.bpe !
Issue -
State: closed - Opened by ngocpham97 about 5 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 about 5 years ago
- 6 comments
#88 - 生成的文本都是乱码
Issue -
State: open - Opened by jason5675 about 5 years ago
- 18 comments
#88 - 生成的文本都是乱码
Issue -
State: open - Opened by jason5675 about 5 years ago
- 18 comments
#87 - 请问只能从零开始训练中文版本的GPT2模型吗?不能基于openai已放出的模型做Finetune吗?
Issue -
State: closed - Opened by jason5675 about 5 years ago
- 1 comment
#87 - 请问只能从零开始训练中文版本的GPT2模型吗?不能基于openai已放出的模型做Finetune吗?
Issue -
State: closed - Opened by jason5675 about 5 years ago
- 1 comment
#86 - 上面那个微信二维码扫码后一直显示查找失败,无法添加。我有个问题想请教:model_config.json中的n_ctx是指什么意思?
Issue -
State: closed - Opened by jason5675 about 5 years ago
- 1 comment
#86 - 上面那个微信二维码扫码后一直显示查找失败,无法添加。我有个问题想请教:model_config.json中的n_ctx是指什么意思?
Issue -
State: closed - Opened by jason5675 about 5 years ago
- 1 comment
#85 - 生成文本出现编码问题
Issue -
State: closed - Opened by ShengXiaoXiao about 5 years ago
- 5 comments
#85 - 生成文本出现编码问题
Issue -
State: closed - Opened by ShengXiaoXiao about 5 years ago
- 5 comments
#84 - Fine tuning on custom language
Issue -
State: closed - Opened by Radeeswar about 5 years ago
- 2 comments
#83 - Can I use it for chatbot?
Issue -
State: closed - Opened by Monica9502 about 5 years ago
- 1 comment
#83 - Can I use it for chatbot?
Issue -
State: closed - Opened by Monica9502 about 5 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 about 5 years ago
#81 - 为什么使用GPU训练的时候,卡在 outputs = model.forward(input_ids=batch_inputs, labels=batch_inputs)
Issue -
State: closed - Opened by gxiskobe about 5 years ago
- 1 comment
#80 - generate时如果设置了生成长度之后生成的内容会被截断,如何解决
Issue -
State: closed - Opened by wusj18 about 5 years ago
- 1 comment
#80 - generate时如果设置了生成长度之后生成的内容会被截断,如何解决
Issue -
State: closed - Opened by wusj18 about 5 years ago
- 1 comment
#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 about 5 years ago
- 1 comment
#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 about 5 years ago
- 1 comment
#78 - 微信交流群
Issue -
State: closed - Opened by Morizeyao about 5 years ago
- 21 comments
#78 - 微信交流群
Issue -
State: closed - Opened by Morizeyao about 5 years ago
- 21 comments
#77 - 训练损失值得问题
Issue -
State: closed - Opened by DarylLei about 5 years ago
- 7 comments
#77 - 训练损失值得问题
Issue -
State: closed - Opened by DarylLei about 5 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 about 5 years ago
- 15 comments
#75 - 训练的时候总是出现这个issue
Issue -
State: closed - Opened by JiaLei123 about 5 years ago
- 2 comments
#75 - 训练的时候总是出现这个issue
Issue -
State: closed - Opened by JiaLei123 about 5 years ago
- 2 comments
#74 - 請問data/tokenized的文件去哪取得
Issue -
State: closed - Opened by cbt36594 about 5 years ago
- 3 comments
#74 - 請問data/tokenized的文件去哪取得
Issue -
State: closed - Opened by cbt36594 about 5 years ago
- 3 comments
#73 - 如何做限定体裁的生成
Issue -
State: closed - Opened by MrRace about 5 years ago
- 1 comment
#73 - 如何做限定体裁的生成
Issue -
State: closed - Opened by MrRace about 5 years ago
- 1 comment
#72 - 训练数据处理的疑问
Issue -
State: closed - Opened by caishiqing about 5 years ago
- 6 comments
#72 - 训练数据处理的疑问
Issue -
State: closed - Opened by caishiqing about 5 years ago
- 6 comments
#71 - 生成效果的疑问
Issue -
State: closed - Opened by caishiqing about 5 years ago
- 4 comments
#71 - 生成效果的疑问
Issue -
State: closed - Opened by caishiqing about 5 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 about 5 years ago
- 3 comments
#69 - 对 total_steps 的估算?
Issue -
State: closed - Opened by xinfeng1i about 5 years ago
- 1 comment
#69 - 对 total_steps 的估算?
Issue -
State: closed - Opened by xinfeng1i about 5 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 about 5 years ago
- 3 comments
#67 - 训练好的模型能提供吗
Issue -
State: closed - Opened by duguiming111 about 5 years ago
- 1 comment
#67 - 训练好的模型能提供吗
Issue -
State: closed - Opened by duguiming111 about 5 years ago
- 1 comment
#66 - 句子的困惑度/得分计算?
Issue -
State: closed - Opened by xinfeng1i about 5 years ago
- 11 comments
#66 - 句子的困惑度/得分计算?
Issue -
State: closed - Opened by xinfeng1i about 5 years ago
- 11 comments
#65 - 训练时候报错RuntimeError: CUDA error: device-side assert triggered
Issue -
State: closed - Opened by yxt132 about 5 years ago
- 28 comments
#65 - 训练时候报错RuntimeError: CUDA error: device-side assert triggered
Issue -
State: closed - Opened by yxt132 about 5 years ago
- 28 comments
#64 - 我有预感,这个技术会跟deepfake一样,逐渐会出现在大众的视野当中
Issue -
State: closed - Opened by atiyit about 5 years ago
- 1 comment
#64 - 我有预感,这个技术会跟deepfake一样,逐渐会出现在大众的视野当中
Issue -
State: closed - Opened by atiyit about 5 years ago
- 1 comment
#63 - 文章摘要生成
Issue -
State: closed - Opened by maozezhong about 5 years ago
- 5 comments
#63 - 文章摘要生成
Issue -
State: closed - Opened by maozezhong about 5 years ago
- 5 comments
#62 - 模型共享
Issue -
State: closed - Opened by chunpingji about 5 years ago
- 1 comment
#62 - 模型共享
Issue -
State: closed - Opened by chunpingji about 5 years ago
- 1 comment
#61 - generate.py中参数batch_size的作用
Issue -
State: closed - Opened by lioyou about 5 years ago
- 4 comments
#60 - gradient_accumulation及warmup_steps参数问题
Issue -
State: closed - Opened by lioyou about 5 years ago
- 3 comments
#60 - gradient_accumulation及warmup_steps参数问题
Issue -
State: closed - Opened by lioyou about 5 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 about 5 years ago
- 2 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 about 5 years ago
- 2 comments
#58 - Improving data processing way to avoid discard data
Pull Request -
State: closed - Opened by lioyou about 5 years ago
#58 - Improving data processing way to avoid discard data
Pull Request -
State: closed - Opened by lioyou about 5 years ago
#57 - 改进数据处理方式避免丢失数据
Pull Request -
State: closed - Opened by lioyou about 5 years ago
- 1 comment
#56 - 参数 n_ctx
Issue -
State: closed - Opened by haif-liu about 5 years ago
- 17 comments
#55 - 训练数据丢失问题
Issue -
State: closed - Opened by lioyou about 5 years ago
- 9 comments
#55 - 训练数据丢失问题
Issue -
State: closed - Opened by lioyou about 5 years ago
- 9 comments
#54 - BPE 使用
Issue -
State: closed - Opened by NiceMartin about 5 years ago
- 9 comments
#54 - BPE 使用
Issue -
State: closed - Opened by NiceMartin about 5 years ago
- 9 comments
#53 - Bugfix: close the file pointer when finishing writing
Pull Request -
State: closed - Opened by xinfeng1i about 5 years ago
#52 - Bug: 文件指针没有被关闭
Issue -
State: closed - Opened by xinfeng1i about 5 years ago
- 2 comments
#49 - 整合快速生成方法和删除无意义代码(Integrate fast generation method and delete meaningless code)
Pull Request -
State: closed - Opened by lioyou about 5 years ago
- 9 comments
#49 - 整合快速生成方法和删除无意义代码(Integrate fast generation method and delete meaningless code)
Pull Request -
State: closed - Opened by lioyou about 5 years ago
- 9 comments
#48 - 整合快速生成方法和删除无意义代码(Integrate fast generation method and delete meaningless code)
Pull Request -
State: closed - Opened by lioyou about 5 years ago
#48 - 整合快速生成方法和删除无意义代码(Integrate fast generation method and delete meaningless code)
Pull Request -
State: closed - Opened by lioyou about 5 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 5 years ago
- 3 comments
#47 - 运行train.py 的时候报错 module 'tensorflow.io' has no attribute 'gfile'
Issue -
State: closed - Opened by JiaLei123 about 5 years ago
- 3 comments
#46 - add fast generate
Pull Request -
State: closed - Opened by fengzuo97 about 5 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 5 years ago
- 6 comments
#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 5 years ago
- 6 comments
#44 - fix mismatched parameter name
Pull Request -
State: closed - Opened by leemengtw about 5 years ago
- 1 comment
#44 - fix mismatched parameter name
Pull Request -
State: closed - Opened by leemengtw about 5 years ago
- 1 comment