Add a model card

README.md

@@ -0,0 +1,30 @@
+---
+language:
+- en
+datasets:
+- pubmed
+- chemical patent
+- recipe
+---
+
+## Proc-RoBERTa
+Proc-RoBERTa is a pre-trained language model for procedural text. It was built by fine-tuning the RoBERTa-based model on a procedural corpus (PubMed articles/chemical patents/cooking recipes), which contains 1.05B tokens. More details can be found in the following [paper](https://arxiv.org/abs/2109.04711):
+
+```
+@article{Bai2021PretrainOA,
+  title={Pre-train or Annotate? Domain Adaptation with a Constrained Budget},
+  author={Fan Bai and Alan Ritter and Wei Xu},
+  journal={ArXiv},
+  year={2021},
+  volume={abs/2109.04711}
+}
+```
+
+## Usage
+```
+from transformers import *
+tokenizer = AutoTokenizer.from_pretrained("fbaigt/proc_roberta")
+model = AutoModelForTokenClassification.from_pretrained("fbaigt/proc_roberta")
+```
+
+More usage details can be found [here](https://github.com/bflashcp3f/ProcBERT).