-
I fine tune chinese_L-12_H-768_A-12 model for my classification tasks, where there are 100 classes, the result is not good as expected, the hyperparametes are: learning rate =2e-5, batch size = 16, …
-
first, thanks your share.
I try to use word vectors to calculate sentence similarity by cos in many time, but it didn't work.
my steps is follow:
1.get two sentence word representations
2.get [CLS…
-
想把chinese_simbert_L-4_H-312_A-12转换成pytorch版本，出现了错误，请问大佬怎么解决呢？
File "E:/project/ws/convert.py", line 63, in
convert_tf_checkpoint_to_pytorch(tf_checkpoint_path, bert_config_file, pytorch_dump_p…
-
```
CUDA_VISIBLE_DEVICES=2,3 python general_distill.py \
--teacher_model /nas/pretrain-bert/pretrain-pytorch/chinese_wwm_ext_pytorch/ \
--stude…
-
总是会报这个错误
ValueError: Could not load model ./data/bert_models/chinese_finetuned_lm/pytorch_model.bin with any of the following classes: (,).
请问您知道是什么原因吗
-
Hi
I'm unable to train.
commit id: 5b538481e24e0d578955be32a95d88fcbde26dc8
Using [melotts_metadata_english.csv](https://github.com/user-attachments/files/16566127/melotts_metadata_english.csv)
W…
mah92 updated
1 month ago
-
E:\Anaconda\lib\site-packages\tensorflow_hub\registry.py in __call__(self, *args, **kwargs)
43 raise RuntimeError(
44 "Missing implementation that supports: %s(*%r, **%r)" % (
…
-
ARG VALUE
__________________________________________________
ckpt_name = bert_model.ckpt
config_name = bert_config.json
cors = *
…
-
这个命名实体识别的算法思路是什么？
-
## Description
## Environment
**TensorRT Version**: 8.5.1.7
**NVIDIA GPU**: V100
**NVIDIA Driver Version**: 470.103.01
**CUDA Version**: 11.8
I used `bert_tf_ckpt_base_qa_squad2_am…