Update README.md

Added more details about the model and usage instructions.

README.md

@@ -9,4 +9,15 @@ datasets:
 - scitail
 language:
 - en
----
+---
+This is an NLI model based on T5-XXL that predicts a binary label (1 - Entailment, 0 - No entailment).
+
+It is trained similarly to the NLI model described in the [TRUE paper (Honovich et al, 2022)](https://arxiv.org/pdf/2204.04991.pdf), but using the following datasets instead of ANLI:
+- SNLI ([Bowman et al., 2015](https://arxiv.org/abs/1508.05326))
+- MNLI ([Williams et al., 2018](https://aclanthology.org/N18-1101.pdf))
+- Fever ([Thorne et al., 2018](https://aclanthology.org/N18-1074.pdf))
+- Scitail ([Khot et al., 2018](http://ai2-website.s3.amazonaws.com/publications/scitail-aaai-2018_cameraready.pdf))
+- PAWS ([Zhang et al. 2019](https://arxiv.org/abs/1904.01130))
+- VitaminC ([Schuster et al., 2021](https://arxiv.org/pdf/2103.08541.pdf))
+
+The input format for the model is: "premise: PREMISE_TEXT hypothesis:HYPOTHESIS_TEXT".