-
# ❓ Questions & Help
## Details
I am trying to continue training my model (gpt-2) from a checkpoint, using Trainer. However when I try to do it the model starts training from 0, not from the che…
fumpe updated
6 months ago
-
### System Info
os: windows server 2019
gpu: A100 40Gb
RAM: 128 GB
python 3.10.11
transformers 4.31.0
pytorch 2.0.1+cu118
### Who can help?
@muellerz
@pacman100
### Information
- […
M98M updated
12 months ago
-
File "E:\work\vits-simple-api\bert_vits2\text\chinese_bert.py", line 35, in get_bert_feature
res = model(**inputs, output_hidden_states=True)
NameError: name 'model' is not defined
-
when I run "from calflops import calculate_flops", the error is showing below:
---------------------------------------------------------------------------
ImportError T…
-
您好，我参照README.md进行配置，在进行到[Evaluate]步骤时出现如下报错
‘’‘
norm lattice embedding
Traceback (most recent call last):
File "/home/ubuntu/anaconda3/envs/nerco/lib/python3.7/site-packages/urllib3/connection…
-
我注意到bert官方提供的中文vocab.txt里，每个汉字都有两个token，一个带有'##'前缀，一个不带前缀，我的理解是不带前缀的表示词的首字，带前缀的是非首字。由于两者转换为id后并不相同，我想请教一下对应词内非首字，训练数据的输入是否使用带前缀的token？另外，MLM的label是否使用带前缀的版本？不胜感激！
-
Hello!
I downloaded the trained checkpoint in README for inferring on the test set to reproduce the results.
The results given in README are (EM / F0.5 : 34.10 / 45.48). But my results (utilizing th…
-
torchsharp有bert微调的相关案例吗，怎么加载pytorch版本的bert呢？
-
I trained the model with the following code：
`python run_mwptoolkit.py --model=MWPBert --dataset=math23k --equation_fix=prefix --task_type=single_equation --pretrained_model=./pretrain/chinese-bert-w…
-
WARNING:tensorflow:From /usr/local/lib/python3.5/dist-packages/tensorflow/python/training/learning_rate_decay_v2.py:321: div (from tensorflow.python.ops.math_ops) is deprecated and will be removed in …