Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

docs: demo, experiments and live inference API on Tiyaro #65

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

docs: demo, experiments and live inference API on Tiyaro #65

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4b752a0
Add badge and links to README.md
ijonglin Sep 2, 2022
04b0fa7
Be more specific with embedded search term
ijonglin Sep 2, 2022
d3209e5
Add section to quick prediction
ijonglin Sep 6, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,16 @@

![Examples image](examples.png)

<p align="center">
<a href="https://console.tiyaro.ai/explore?q=toxic-bert&pub=unitary"> <img src="https://tiyaro-public-docs.s3.us-west-2.amazonaws.com/assets/try_on_tiyaro_badge.svg"></a>
</p>


## News & Updates

### 02-09-2022: Live Demo and APIs available at Tiyaro.ai
- Try out the hosted [API and visualizer](https://console.tiyaro.ai/explore/unitary-toxic-bert/demo)

### 22-10-2021: New improved multilingual model & standardised class names
- Updated the `multilingual` model weights used by Detoxify with a model trained on the translated data from the 2nd Jigsaw challenge (as well as the 1st). This model has also been trained to minimise bias and now returns the same categories as the `unbiased` model. New best AUC score on the test set: 92.11 (89.71 before).
- All detoxify models now return consistent class names (e.g. "identity_attack" replaces "identity_hate" in the `original` model to match the `unbiased` classes).
Expand Down Expand Up @@ -107,8 +115,15 @@ import pandas as pd
print(pd.DataFrame(results, index=input_text).round(5))

```

For more details check the Prediction section.

### Hosted APIs for Quick Prediction

Alternatively, you may experiment with the detoxify model as a hosted API:

- [Unitary Toxic BERT Model Card on Tiyaro.ai](https://console.tiyaro.ai/explore/unitary-toxic-bert/api)


## Labels
All challenges have a toxicity label. The toxicity labels represent the aggregate ratings of up to 10 annotators according the following schema:
Expand Down