-
使用bert4keras训练的BERT分类模型经过转换后报错提示有3个OP不支持转换：
paddle.__version__ = 1.7.2
Now translating model from tensorflow to paddle.
Shape[now is [-1, -1]] for input tensor[tensor name: "Input-Token"] not sup…
-
前两天用电脑训练了一个《鬼吹灯》的文本生成模型，不生用题主的代码，基于“抱抱脸（Huggingface）”发布的GPT2生成模型改的，文本组成：
- 鬼吹灯 1 精绝古城
- 鬼吹灯 2 龙岭迷窟
- 鬼吹灯 3 云南虫谷
- 鬼吹灯 4 昆仑神宫
- 鬼吹灯 5 黄皮子坟
- 鬼吹灯 6 南海归墟
- 鬼吹灯 7 怒晴湘西
- 鬼吹灯 8 巫峡棺山
…
-
使用docker部署，环境为ubuntu 24
在 admin 选择模型加载后无反应，查询日志如下
```
2024-07-27 21:47:03 [INFO] Loading model model_path: model1/604_epochs.pth config_path: model1/config.json [in views.load_model:74]
[2024-…
-
**版本信息：**
paddle.__version__
'1.8.3'
paddlehub.__version__
'1.8.0'
win10
**在运行PaddleHub/demo/senta/senta_finetune.py时报错**
----------------------
Error Message Summary:
-------------------…
-
2024年6月份，没有代理和梯子huggingface_hu 无法访问。查找资料后
安装huggingface_hub：6月份版本是Version: 0.23.4
1.pip install -U huggingface_hub
2.export HF_ENDPOINT=https://hf-mirror.com
3.huggingface-cli download --resume-do…
-
Hi! I managed to train LAS on aishell data without errors. This is the end of the log:
```
Epoch 20 | Iter 441 | Average Loss 0.406 | Current Loss 0.505424 | 64.8 ms/batch
Epoch 20 | Iter 451 | A…
-
Subscribe to this issue and stay notified about new [daily trending repos in Python](https://github.com/trending/python?since=daily).
-
Post a link for a "possibility" reading of your own on the topic of Deep Learning with Text [for week 5], accompanied by a 300-400 word reflection that: 1) briefly summarizes the article (e.g., as we …
lkcao updated
2 years ago
-
numpy.core._exceptions._ArrayMemoryError: Unable to allocate 550. GiB for an array with shape (28235788,) and data type |S20921
How did you solve this mistake? The pre training corpus is read incorre…
-
下载`chinese_pretrain_mrc_roberta_wwm_ext_large ` 到本地
参数为：
```
model_name = "roberta_wwm_ext_large" # "chinese_pretrain_mrc_macbert_large"
model_type = 'bert'
threads = 24
eval_batch_size = 64
…