First-pass at putting current summary in Model Card format

This takes the writing that was already here and organizes it into the Model Card protocol.
Still more work to do, but it makes information about the model more easily findable.

README.md

@@ -2,12 +2,31 @@
 language: en
 license: mit
 widget:
-- text: "COVID-19 is"
+- text: COVID-19 is
+metrics:
+- accuracy
+- f1
 ---
 
-## BioGPT
+# Model Card for BioGPT
 
-Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain. Among the two main branches of pre-trained language models in the general language domain, i.e. BERT (and its variants) and GPT (and its variants), the first one has been extensively studied in the biomedical domain, such as BioBERT and PubMedBERT. While they have achieved great success on a variety of discriminative downstream biomedical tasks, the lack of generation ability constrains their application scope. In this paper, we propose BioGPT, a domain-specific generative Transformer language model pre-trained on large-scale biomedical literature. We evaluate BioGPT on six biomedical natural language processing tasks and demonstrate that our model outperforms previous models on most tasks. Especially, we get 44.98%, 38.42% and 40.76% F1 score on BC5CDR, KD-DTI and DDI end-to-end relation extraction tasks, respectively, and 78.2% accuracy on PubMedQA, creating a new record. Our case study on text generation further demonstrates the advantage of BioGPT on biomedical literature to generate fluent descriptions for biomedical terms.
+BioGPT is a domain-specific generative Transformer language model pre-trained on large-scale biomedical literature.
+
+## Model Details
+
+### Model Description
+
+Pre-trained language models have attracted increasing attention in the biomedical domain, 
+inspired by their great success in the general natural language domain. 
+Among the two main branches of pre-trained language models in the general language domain, 
+i.e., BERT (and its variants) and GPT (and its variants), the first one has been extensively studied in the biomedical domain, 
+such as BioBERT and PubMedBERT. While they have achieved great success on a variety of discriminative downstream biomedical tasks, 
+the lack of generation ability constrains their application scope. 
+
+BioGPT addresses the need for generation abilities, implemented as a domain-specific generative Transformer language model 
+pre-trained on large-scale biomedical literature. 
+
+### How to Get Started with the Model
 
 You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we
 set a seed for reproducibility:
@@ -63,6 +82,36 @@ tokenizer.decode(beam_output[0], skip_special_tokens=True)
 'COVID-19 is a global pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the causative agent of coronavirus disease 2019 (COVID-19), which has spread to more than 200 countries and territories, including the United States (US), Canada, Australia, New Zealand, the United Kingdom (UK), and the United States of America (USA), as of March 11, 2020, with more than 800,000 confirmed cases and more than 800,000 deaths.'
 ```
 
+
+## Evaluation
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+Six biomedical natural language processing tasks.
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+ - F1, for end-to-end relation extraction tasks
+ - Accuracy, on PubMedQA
+
+### Results
+
+The model achieves 44.98%, 38.42% and 40.76% F1 score on BC5CDR, KD-DTI and DDI end-to-end relation extraction tasks, 
+respectively, and 78.2% accuracy on PubMedQA, creating a new record. 
+
+#### Summary
+
+This model outperforms previous models on most evaluated tasks. 
+
+Our case study on text generation further demonstrates the advantage of BioGPT on biomedical literature to 
+generate fluent descriptions for biomedical terms.
+
 ## Citation
 
 If you find BioGPT useful in your research, please cite the following paper:
@@ -83,4 +132,4 @@ If you find BioGPT useful in your research, please cite the following paper:
     note = {bbac409},
     eprint = {https://academic.oup.com/bib/article-pdf/23/6/bbac409/47144271/bbac409.pdf},
 }
-```
+```