-
### System Info
Ubuntu 22.02 on AWS running on a m5.4xlarge instance. The code is running in the context of a Laravel application (specifically a mixin for `Illuminate\Support\Str`), being tested v…
-
**Version**
See the console output for PyABSA, Torch, Transformers Version
2.4.1.post1
**Describe the bug**
A clear and concise description of what the bug is.
Traceback (most recent call last)…
sqs17 updated
7 months ago
-
The best finetune result(finetune from the pretrain model you published) I get is 56.62,83.96,90.56 which is still 1.6 lower than your reported result, furthermore, the zero-shot evaluation result fro…
-
### 🐛 Describe the bug
`BertForMaskedLM`, `BertForQuestionAnswering`, `CamemBert`, `RobertaForCausalLM`, `RobertaForQuestionAnswering` in HF fail with `Constraints violated` using transformers `v4.31…
-
do this by removing everything before "ounce|ounces" and after "(preferably"
-
Thanks for providing this code. I'd love to use it, but am getting the following error when running the trainer.
```
(py38_test) [richier@reslnapollo02 transformers_ner]$ python bert_crf_trainer.p…
-
*前置说明：**如果大概率出现重复引导音频，就不是本问题的描述范围，可能是引导音频的原因。** **使用的是 fast_inference 分支**
问题描述：
并发批量测试的时候，固定随机种子与文本，有概率出现 1-2 个任务结果与其他任务结果不同，有 **吞句，重复，首句重复引导音频** 的问题。
主要表现为重复一句话，吞了下一句话。
可能原因：
通过打 log 定位，应该是…
-
# 🚀 Feature request
Extract the `do_lower_case` option to make it available for any tokenizer. Not just those that initially supported this, like the `BERT` tokenizers.
## Motivation
Sometime…
-
Hello! I was wondering if you would release your pretraining code for DNABERT-2 and NT? The DNABERT-2 website does not release the actual code that they used to pre-train, just a suggestion of two sim…
-
Instead of adam.
https://arxiv.org/pdf/1908.03265v1
Lookahead merits to be tried too https://arxiv.org/pdf/1907.08610v1.pdf
Maybe it can be used on top of RAdam.