-
-
微博内容精选
-
Greetings, DeeBERT is really a crucial and easy-to-understand achievement in BERT inference acceleration.
However, in `transformers/modeling_highway_bert.py`, the `forward` function of class `BertH…
sbwww updated
2 years ago
-
When calculating entropy, `dim=1` is better to be replaced with `dim=-1`, since `num_labels` is **the last** dimension of logits but **not always the 2nd** dimension (e.g., in Token Classification, `…
sbwww updated
2 years ago
-
**Is your feature request related to a problem? Please describe.**
During a single inference session, is there a way to stop the execution earlier before finishing all the nodes in the graph based on…
-
After the conversion we ended up with inconsistent values for `defaults to` - sometimes it's `formatted`, other times it's *italics*, with former being the prevailing form. Example:
```
src/transfor…
-
# 🌟 New model addition
## Model description
We just open-sourced [FastFormers](https://arxiv.org/abs/2010.13382) which are our SustaiNLP 2020 systems (FastFormers: Highly Efficient Transformer M…
-
I'm working on making the tests work under multiple gpus and run into and this one that proved to be stubborn, for some reason it doesn't work under any DP scheme. I don't know anything about this scr…
-
`DeeBertTests.test_glue_deebert`
Excerpt from [CI](https://pipelines.actions.githubusercontent.com/SFFqAjp6ciVZiZmfZfjie9y9Q96dfpUE8sJvWAtTDWoFlixGkf/_apis/pipelines/1/runs/4783/signedlogcontent/3?ur…