Update README.md

README.md

@@ -1,3 +1,81 @@
 ---
-license: mit
+language:
+- en
+license:
+- mit
+library_name: "pytorch"
+multilinguality:
+- monolingual
+pretty_name: perturber
+datasets:
+- panda
+tags:
+- counterfactual
+- perturb
+- fairness
+- nlp
+- demographic
+- diverse
+- gender
+- non-binary
+- race
+- age
+metrics:
+- bleu
 ---
+
+# Model Card for the perturber
+
+## Table of Contents
+- [Table of Contents](#table-of-contents)
+- [Model Description](#model-description)
+  - [Model Summary](#dataset-summary)
+  - [Languages](#languages)
+- [Dataset Structure](#dataset-structure)
+  - [Data Instances](#data-instances)
+  - [Data Fields](#data-fields)
+  - [Data Splits](#data-splits)
+- [Dataset Creation](#dataset-creation)
+  - [Curation Rationale](#curation-rationale)
+  - [Source Data](#source-data)
+  - [Annotations](#annotations)
+  - [Personal and Sensitive Information](#personal-and-sensitive-information)
+- [Considerations for Using the Data](#considerations-for-using-the-data)
+  - [Social Impact of Dataset](#social-impact-of-dataset)
+  - [Discussion of Biases](#discussion-of-biases)
+  - [Other Known Limitations](#other-known-limitations)
+- [Additional Information](#additional-information)
+  - [Dataset Curators](#dataset-curators)
+  - [Licensing Information](#licensing-information)
+  - [Citation Information](#citation-information)
+  - [Contributions](#contributions)
+
+## Model Description
+
+The perturber is a seq2seq controlled generation model that rewrites text along a specified demographic axis and attribute.
+
+The perturber takes in (i) a source text snippet, (ii) a word in the snippet referring to a demographic group, and (iii) a new target demographic attribute, and generates a perturbed snippet that refers to the target demographic attribute, while preserving overall meaning.
+
+- **Repository:** https://github.com/facebookresearch/ResponsibleNLP/
+- **Paper:** https://arxiv.org/abs/2205.12586
+- **Point of Contact:** [email protected], [email protected], [email protected], [email protected]
+- **License:** MIT
+
+### Model Summary
+
+The perturber is a finetuned BART model (Lewis et al., 2020) with 24 layers, 1024 hidden size, 406M parameters, and 16 attention heads. To train the perturber in the original paper, we finetune BART on PANDA using the ParlAI library.
+
+This model release is separately trained using the HuggingFace transformers library, with the same parameters as the ParlAI model.
+
+Currently the perturber supports text rewriting along three axes and several attributes:
+- **gender:** man, woman, non-binary
+- **race:** black, white, asian, hispanic, native-american, pacific-islander
+- **age:** child, young, middle-aged, senior, adult
+
+### Uses
+
+The perturber is intended for use by fairness researchers and engineers working on demographic debiasing applications. The perturber supports counterfactual perturbation augmentation.
+
+### Contributions
+
+Thanks to [@Rebecca-Qian](https://github.com/Rebecca-Qian) for adding this model.