Update article_classification_modelcard.md

article_classification_modelcard.md

@@ -20,7 +20,7 @@ This model has been fine-tuned to classify scientific articles (title and abstra
 - **Model type:** RoBERTa (BERT; Transformer)
 - **Language(s) (NLP):** Python
 - **License:** MIT
-- **Finetuned from model:** [transformers.AutoModelForSequenceClassification()](https://huggingface.co/docs/transformers/model_doc/auto)
+- **Finetuned from model:** https://huggingface.co/allenai/dsp_roberta_base_dapt_biomed_tapt_rct_500
 
 ## Model Sources
 
@@ -112,15 +112,16 @@ The model works satisfactorily for identifying articles describing biodata resou
 
 ## Model Architecture and Objective
 
-[More Information Needed]
+The base model architecture is as described in [Gururangan S., *et al.,* 2020](http://arxiv.org/abs/2004.10964). Classification is performed using
+a linear sequence classification layer initialized using [transformers.AutoModelForSequenceClassification()](https://huggingface.co/docs/transformers/model_doc/auto).
 
 ## Compute Infrastructure
 
-[More Information Needed]
+Model was fine-tuned on Google Colaboratory.
 
 ### Hardware
 
-Model was fine-tuned on Google Colaboratory using GPU acceleration.
+Model was fine-tuned using GPU acceleration provided by Google Colaboratory.
 
 ### Software