Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / lonepatient/albert_pytorch issues and pull requests
#71 - tf模型转换pt失败
Issue -
State: closed - Opened by wqw547243068 about 1 year ago
- 2 comments
#71 - tf模型转换pt失败
Issue -
State: closed - Opened by wqw547243068 about 1 year ago
- 2 comments
#70 - 请教一下,您这边给出来的pytorch的albert预训练模型是谷歌经过大量语料训练出来的吗
Issue -
State: open - Opened by hfy-only almost 2 years ago
- 2 comments
#70 - 请教一下,您这边给出来的pytorch的albert预训练模型是谷歌经过大量语料训练出来的吗
Issue -
State: open - Opened by hfy-only almost 2 years ago
- 2 comments
#69 - 请问optimizer.bin 这个文件要去哪里下载?谢谢
Issue -
State: open - Opened by lsx0930 over 2 years ago
#69 - 请问optimizer.bin 这个文件要去哪里下载?谢谢
Issue -
State: open - Opened by lsx0930 over 2 years ago
#68 - run_pretraining.py可能缺少调用main函数的地方
Issue -
State: open - Opened by Freeshman over 2 years ago
#67 - BertLayer第二个子层为何有两个nn.Linear
Issue -
State: open - Opened by aibeiyun almost 3 years ago
#67 - BertLayer第二个子层为何有两个nn.Linear
Issue -
State: open - Opened by aibeiyun almost 3 years ago
#66 - 训练时显存占用问题
Issue -
State: open - Opened by Qiu-dot over 3 years ago
#66 - 训练时显存占用问题
Issue -
State: open - Opened by Qiu-dot over 3 years ago
#65 - create_masked_lm_predictions()
Issue -
State: closed - Opened by flyerjia over 3 years ago
#65 - create_masked_lm_predictions()
Issue -
State: closed - Opened by flyerjia over 3 years ago
#64 - 请问可以使用pytorch的版本重新进行预训练吗?如果可以,应该怎么做?
Issue -
State: closed - Opened by yysirs over 3 years ago
#64 - 请问可以使用pytorch的版本重新进行预训练吗?如果可以,应该怎么做?
Issue -
State: closed - Opened by yysirs over 3 years ago
#63 - tf模型转pytorch模型报错?
Issue -
State: closed - Opened by ghost over 3 years ago
- 1 comment
#63 - tf模型转pytorch模型报错?
Issue -
State: closed - Opened by ghost over 3 years ago
- 1 comment
#62 - readme中fine-tune结果的超参数
Issue -
State: open - Opened by Sisi0518 almost 4 years ago
#62 - readme中fine-tune结果的超参数
Issue -
State: open - Opened by Sisi0518 almost 4 years ago
#61 - No such file or directory
Issue -
State: open - Opened by ShaoaAllen almost 4 years ago
#61 - No such file or directory
Issue -
State: open - Opened by ShaoaAllen almost 4 years ago
#60 - 基于albert模型继续在自己的数据集上pretraining albert的问题
Issue -
State: closed - Opened by liuxiaohao-xn about 4 years ago
- 2 comments
#60 - 基于albert模型继续在自己的数据集上pretraining albert的问题
Issue -
State: closed - Opened by liuxiaohao-xn about 4 years ago
- 2 comments
#59 - 转换模型时出错
Issue -
State: open - Opened by llxbush about 4 years ago
#59 - 转换模型时出错
Issue -
State: open - Opened by llxbush about 4 years ago
#58 - AlbertForNextSentencePredicition
Issue -
State: open - Opened by DeepakDhanasekar about 4 years ago
- 2 comments
#58 - AlbertForNextSentencePredicition
Issue -
State: open - Opened by DeepakDhanasekar about 4 years ago
- 2 comments
#57 - 如何加入重计算机制(torch.utils.checkpoint)
Issue -
State: open - Opened by ReyonRen about 4 years ago
#57 - 如何加入重计算机制(torch.utils.checkpoint)
Issue -
State: open - Opened by ReyonRen about 4 years ago
#56 - TF_WEIGHTS_NAME = 'model.ckpt'里面的model.ckpt文件在哪里?
Issue -
State: open - Opened by yexingxin about 4 years ago
#55 - What is the relationship between learning rate and BERT model size (especially the depth)
Issue -
State: open - Opened by wsn555 over 4 years ago
#55 - What is the relationship between learning rate and BERT model size (especially the depth)
Issue -
State: open - Opened by wsn555 over 4 years ago
#54 - 将brightmart中预训练的TensorFlow模型转换为Pytorch模型报如下错误,'Embedding' object has no attribute 'shape'
Issue -
State: open - Opened by wyqnumber over 4 years ago
#53 - ALBERT-small训练效果问题
Issue -
State: open - Opened by Hanlard over 4 years ago
#53 - ALBERT-small训练效果问题
Issue -
State: open - Opened by Hanlard over 4 years ago
#52 - 关于继续在Classification问题上finetune的问题
Issue -
State: closed - Opened by zipzou over 4 years ago
#52 - 关于继续在Classification问题上finetune的问题
Issue -
State: closed - Opened by zipzou over 4 years ago
#51 - 生成GLUE提交版本文件
Issue -
State: closed - Opened by Lillian9707 over 4 years ago
#51 - 生成GLUE提交版本文件
Issue -
State: closed - Opened by Lillian9707 over 4 years ago
#50 - global_step的位置导致多次执行无谓的evaluate()
Issue -
State: open - Opened by illusions-LYY over 4 years ago
#50 - global_step的位置导致多次执行无谓的evaluate()
Issue -
State: open - Opened by illusions-LYY over 4 years ago
#49 - not initialized from pretrained model: ['bert.albert.embeddings.word_embeddings.weight', 'bert.albert.embeddings.position_embeddings.weight', 'bert.albert.embeddings.token_type_embeddings.weight',
Issue -
State: closed - Opened by yc0815024 over 4 years ago
- 4 comments
#49 - not initialized from pretrained model: ['bert.albert.embeddings.word_embeddings.weight', 'bert.albert.embeddings.position_embeddings.weight', 'bert.albert.embeddings.token_type_embeddings.weight',
Issue -
State: closed - Opened by yc0815024 over 4 years ago
- 4 comments
#48 - No Factorization?
Issue -
State: closed - Opened by SCNUJackyChen over 4 years ago
- 1 comment
#47 - How can I do MLM task on new dataset with new vocab.txt utilizing AlbertForPreTraining with pretrained weights?
Issue -
State: open - Opened by ChineseYjh over 4 years ago
#46 - 加载Brightmart模型时,AlbertForMaskedLM中的cls.predictions.project_layer参数无法正确加载
Issue -
State: open - Opened by hong-feng over 4 years ago
- 5 comments
#46 - 加载Brightmart模型时,AlbertForMaskedLM中的cls.predictions.project_layer参数无法正确加载
Issue -
State: open - Opened by hong-feng over 4 years ago
- 5 comments
#45 - “pooled_output = self.dropout(pooled_output+0.1)” is confusing
Issue -
State: closed - Opened by matricer over 4 years ago
- 1 comment
#45 - “pooled_output = self.dropout(pooled_output+0.1)” is confusing
Issue -
State: closed - Opened by matricer over 4 years ago
- 1 comment
#44 - 关于继续pretrain的问题
Issue -
State: closed - Opened by SCNUJackyChen over 4 years ago
- 5 comments
#43 - How can I do when there is only 1 sentence in a document?
Issue -
State: closed - Opened by SCNUJackyChen almost 5 years ago
- 2 comments
#43 - How can I do when there is only 1 sentence in a document?
Issue -
State: closed - Opened by SCNUJackyChen almost 5 years ago
- 2 comments
#42 - sentence-order prediction
Issue -
State: open - Opened by qiunlp almost 5 years ago
- 4 comments
#42 - sentence-order prediction
Issue -
State: open - Opened by qiunlp almost 5 years ago
- 4 comments
#41 - AlbertForNextSentencePrediction
Issue -
State: closed - Opened by qiunlp almost 5 years ago
- 3 comments
#41 - AlbertForNextSentencePrediction
Issue -
State: closed - Opened by qiunlp almost 5 years ago
- 3 comments
#40 - delete unnecessary assertion
Issue -
State: closed - Opened by SCNUJackyChen almost 5 years ago
#40 - delete unnecessary assertion
Issue -
State: closed - Opened by SCNUJackyChen almost 5 years ago
#39 - How can i use albert to finish CLOTH test? I need some suggestion. Thank you.
Issue -
State: open - Opened by jiangjiaqi6 almost 5 years ago
- 1 comment
#39 - How can i use albert to finish CLOTH test? I need some suggestion. Thank you.
Issue -
State: open - Opened by jiangjiaqi6 almost 5 years ago
- 1 comment
#38 - Couldn't find 'checkpoint' file or checkpoints in given directory
Issue -
State: closed - Opened by jiangjiaqi6 almost 5 years ago
- 7 comments
#37 - tensorflow到pytorch版本模型转换错误
Issue -
State: closed - Opened by Zessay almost 5 years ago
- 4 comments
#37 - tensorflow到pytorch版本模型转换错误
Issue -
State: closed - Opened by Zessay almost 5 years ago
- 4 comments
#36 - 咨询albert在huggingface/transformers下的使用
Issue -
State: closed - Opened by renjunxiang almost 5 years ago
- 6 comments
#36 - 咨询albert在huggingface/transformers下的使用
Issue -
State: closed - Opened by renjunxiang almost 5 years ago
- 6 comments
#35 - 与当前huggingface/transformers的代码不兼容
Issue -
State: closed - Opened by ghost almost 5 years ago
- 3 comments
#34 - AttributeError: 'AlbertForSequenceClassification' object has no attribute 'keys'
Issue -
State: open - Opened by chiragsanghvi10 almost 5 years ago
#33 - [Question] 为什么在中文版本使用bert标准分词,英文版本使用sentencepiece分词啊?
Issue -
State: closed - Opened by sakuranew almost 5 years ago
- 3 comments
#32 - albert_tiny_google_zh convert to pytorch
Issue -
State: closed - Opened by miangangzhen almost 5 years ago
- 2 comments
#32 - albert_tiny_google_zh convert to pytorch
Issue -
State: closed - Opened by miangangzhen almost 5 years ago
- 2 comments
#31 - 能不能用albert_chinese_pytorch代码做英文语料的预训练
Issue -
State: closed - Opened by shenlanyilang almost 5 years ago
- 2 comments
#31 - 能不能用albert_chinese_pytorch代码做英文语料的预训练
Issue -
State: closed - Opened by shenlanyilang almost 5 years ago
- 2 comments
#30 - 请问能否支持一下Lamb optimizer
Issue -
State: closed - Opened by lxl910915 almost 5 years ago
- 2 comments
#30 - 请问能否支持一下Lamb optimizer
Issue -
State: closed - Opened by lxl910915 almost 5 years ago
- 2 comments
#29 - 跑seq=1024,batch_szie=2,1万步左右loss会变成nan,是不是因为batch_size太小了
Issue -
State: closed - Opened by lxl910915 almost 5 years ago
#28 - 训练过程中albert占用的显存很大
Issue -
State: open - Opened by fatmelon almost 5 years ago
- 3 comments
#27 - CUDA error: no kernel image is available for execution on the device
Issue -
State: closed - Opened by chiragsanghvi10 about 5 years ago
- 1 comment
#26 - 这个断言可以修改一下,前面内循环判断。 if len(masked_token_labels) >= num_to_mask:
Issue -
State: open - Opened by moonblue333 about 5 years ago
- 2 comments
#26 - 这个断言可以修改一下,前面内循环判断。 if len(masked_token_labels) >= num_to_mask:
Issue -
State: open - Opened by moonblue333 about 5 years ago
- 2 comments
#25 - RuntimeError: Error(s) in loading state_dict for BertModel
Issue -
State: open - Opened by ZiteHe about 5 years ago
- 1 comment
#25 - RuntimeError: Error(s) in loading state_dict for BertModel
Issue -
State: open - Opened by ZiteHe about 5 years ago
- 1 comment
#24 - 使用albert.base(英文)finetuning的时候,--gradient_accumulation_steps设置为大于1时直接进入evaluating而不training
Issue -
State: open - Opened by YuxiangLu about 5 years ago
- 1 comment
#24 - 使用albert.base(英文)finetuning的时候,--gradient_accumulation_steps设置为大于1时直接进入evaluating而不training
Issue -
State: open - Opened by YuxiangLu about 5 years ago
- 1 comment
#23 - 请教下share_type和embedding_size的选择上有什么建议吗
Issue -
State: closed - Opened by BaeSeulki about 5 years ago
- 1 comment
#23 - 请教下share_type和embedding_size的选择上有什么建议吗
Issue -
State: closed - Opened by BaeSeulki about 5 years ago
- 1 comment
#22 - 请问如何使用微调好的模型进行预测?
Issue -
State: open - Opened by zhu1090093659 about 5 years ago
- 1 comment
#22 - 请问如何使用微调好的模型进行预测?
Issue -
State: open - Opened by zhu1090093659 about 5 years ago
- 1 comment
#21 - fix: remove appending variables/variables to the tfpath
Pull Request -
State: open - Opened by Porcupine96 about 5 years ago
#21 - fix: remove appending variables/variables to the tfpath
Pull Request -
State: open - Opened by Porcupine96 about 5 years ago
#20 - tf_path in the english model
Issue -
State: open - Opened by Porcupine96 about 5 years ago
- 1 comment
#20 - tf_path in the english model
Issue -
State: open - Opened by Porcupine96 about 5 years ago
- 1 comment
#19 - 导出至TorchScript
Issue -
State: closed - Opened by gitabtion about 5 years ago
- 4 comments
#19 - 导出至TorchScript
Issue -
State: closed - Opened by gitabtion about 5 years ago
- 4 comments
#18 - 关于xlarge模型的batch_size和学习率
Issue -
State: open - Opened by DunZhang about 5 years ago
- 2 comments
#18 - 关于xlarge模型的batch_size和学习率
Issue -
State: open - Opened by DunZhang about 5 years ago
- 2 comments
#17 - 转换模型就段错误了~~
Issue -
State: closed - Opened by Zawo1995 about 5 years ago
- 2 comments
#17 - 转换模型就段错误了~~
Issue -
State: closed - Opened by Zawo1995 about 5 years ago
- 2 comments
#16 - 在自己的数据集上继续fineturning
Issue -
State: open - Opened by woyijkl1 about 5 years ago
- 11 comments
#16 - 在自己的数据集上继续fineturning
Issue -
State: open - Opened by woyijkl1 about 5 years ago
- 11 comments
#15 - Segmentation fault (core dumped)
Issue -
State: closed - Opened by tedljw about 5 years ago
- 6 comments