Update model card

README.md

@@ -1,6 +1,15 @@
+---
+language: 
+- en
+tags:
+- nlp
+- math learning
+- education
+license: mit
+---
 # Math-RoBerta for NLP tasks in math learning environments
 
-This model is fine-tuned with RoBERTa-large with over 3,000,000 posts and replies from students and instructors in Algebra Nation (https://www.mathnation.com/). It can potentially provide a good base performance on NLP related tasks in similar math learning environments.
+This model is fine-tuned RoBERTa-large trained with 8 Nvidia RTX 1080Ti GPUs using 3,000,000 math discussion posts by students and facilitators on Algebra Nation (https://www.mathnation.com/). MathRoBERTa has 24 layers, and 355 million parameters and its published model weights take up to 1.5 gigabytes of disk space. It can potentially provide a good base performance on NLP related tasks (e.g., text classification, semantic search, Q&A) in similar math learning environments.
 
 ### Here is how to use it with texts in HuggingFace
 ```python