-
想问一下您当时使用的paddlepaddle,paddlehub还有wwm_bert的版本都是什么呢?finetune_and_eval()模型训练的时候总是报错——RuntimeError: parallel_for failed: no kernel image is available for execution on the device
-
Hello, thank you so much for your work.
I'm trying to use the FlopCountAnalysis class but I'm not able to free the GPU memory used.
As a minimal example, without the FlopCountAnalysis I can do s…
-
尝试过bert-wwm(哈工大提供的),在keras上面可以跑batch_size=6,max_seq=512。
但是,在这里面只能跑batch=1,seq_len=300(我试过)
版本、环境信息:
1)PaddlePaddle版本:1.5.0.post87
2)CPU:i5 9400f
3)GPU:1080ti,通过anaconda安装的cudatoolkit 8.0,cudnn7…
-
ImportError: RobertaModel requires the Pytorch library but it was not found in your environment...
但是我这边环境检查了多次是没有问题的
BD-MF updated
2 years ago
-
hi大佬,请问下这边几个文件是不是没有上传呀
self.dict_path = 'E:/bert_weight_files/roberta/vocab.txt'
self.config_path='E:/bert_weight_files/roberta/bert_config_rbt3.json'
self.checkpoint_path='…
-
您好,我注意到 您之前的工作中https://github.com/taishan1994/pytorch_bert_event_extraction 写道“要预先下载好[chinese-roberta-wwm-ext](https://huggingface.co/hfl/chinese-roberta-wwm-ext/tree/main)模型,并在运行时指定模型的位置。
已经训练好的模型…
-
I try to run code like this
```
python3 run_squad.py \
--model_type bert \
--model_name_or_path bert-large-uncased-whole-word-masking \
--do_train \
--do_eval \
--do_lower_c…
-
谢谢您的代码,数据处理完后,运行train.py,有配置json和预训练模型,我是不是nlp方向的的小白,想试试,求指点,这个目录从哪里获取
-
-
Hi,
Thanks for the good job!
Is it possible to use these models with spaCy 3.0? Is there some recipe to this use? (actually the spaCy page about Transformers is not clear on how to train a new pipel…