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

minor model card description updates #8051

Merged
merged 1 commit into from
Oct 26, 2020
Merged

minor model card description updates #8051

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 5 additions & 6 deletions model_cards/joeddav/xlm-roberta-large-xnli/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,8 +24,6 @@ widget:

This model takes [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) and fine-tunes it on a combination of NLI data in 15 languages. It is intended to be used for zero-shot text classification, such as with the Hugging Face [ZeroShotClassificationPipeline](https://huggingface.co/transformers/master/main_classes/pipelines.html#transformers.ZeroShotClassificationPipeline).

You can play with an interactive demo of this zero-shot technique with this model [here](https://huggingface.co/zero-shot/).

## Inteded Usage

This model is intended to be used for zero-shot text classification, especially in languages other than English. It is fine-tuned on XNLI, which is a multilingual NLI dataset. The model can therefore be used with any of the languages in the XNLI corpus:
Expand All @@ -46,13 +44,14 @@ This model is intended to be used for zero-shot text classification, especially
- Swahili
- Urdu

Since the base model was pre-trained trained on 100 different languages (see the full list in appendix A of the [XLM
Roberata paper](https://arxiv.org/abs/1911.02116)), the model may have some limited effectiveness in other languages as
well.
Since the base model was pre-trained trained on 100 different languages, the
model has shown some effectiveness in languages beyond those listed above as
well. See the full list of pre-trained languages in appendix A of the
[XLM Roberata paper](https://arxiv.org/abs/1911.02116)

For English-only classification, it is recommended to use
[bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) or
[bart-large-mnli-yahoo-answers](https://huggingface.co/joeddav/bart-large-mnli-yahoo-answers).
[a distilled bart MNLI model](https://huggingface.co/models?filter=pipeline_tag%3Azero-shot-classification&search=valhalla).

#### With the zero-shot classification pipeline

Expand Down