-
It would be great if you could add the exact mixture used to train FLAN-T5 and FLAN-UL2. This is not trivial because it doesn't look like limiting the number of examples per task is implemented in thi…
-
Hi,
Thanks for releasing the code for this amazing paper.
I want to ask some questions about the length parameters of the get_delta function ([this link](https://github.com/kongds/Prompt-BERT/bl…
-
When running
```
python infer_bert.py --from-files ../data/texts-inosmi-rus/e1.txt \
--labels-count 3 \
--terms-per-context 50 \
--tokens-per-context 128 \
--text-b-type nli_m \
…
-
I keep encountering the following error:
Seems to occur on the entire website, but only on my ma…
-
### What happened?
I can't receive any new emails after importing a maildir exported using mbsync from a https://maddy.email server
### How can we reproduce the problem?
I exported my emails …
33KK updated
11 months ago
-
https://github.com/huggingface/datasets/releases/tag/2.14.0
main changes:
- use `token` instead of `use_auth_token`
- the default config name is now `default` instead of `username--dataset_name`:…
-
Hi guys. I just try to follow the training_stsbenchmark_continue_training.py to build my own model. But my model and these examples both show the error. I did not make any changes to the training_stsb…
-
```
import pycorrector
corrected_sent, detail = pycorrector.correct('少先队员因该为老人让坐')
```
接口上使用的是上面这种代码，处理单条文本，目前调用的延迟有3s。
个人猜测是每次调用的时候，每次都会重新加载kenlm模型，导致时间消耗太多。
如果这样，有什么方法是加载一次模型就可以的？个人尝试了如下方法：
`…
-
As dicussed in our meeting some time ago we need to move the repositories to a different account.
To avoid any issues with ongoing release cycles, the switch will happen on April 27th, 2023 after t…
-
### Model description
[XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models](https://arxiv.org/abs/2301.10472)
Large multilingual language models typically rely on a …