Update README.md

README.md

@@ -1,4 +1,10 @@
-[bioformer-cased-v1.0](https://huggingface.co/bioformers/bioformer-cased-v1.0) fined-tuned on the [SQuAD1](https://rajpurkar.github.io/SQuAD-explorer) dataset for 3 epochs.
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: question-answering
+---
+[bioformer-8L](https://huggingface.co/bioformers/bioformer-8L) fined-tuned on the [SQuAD1](https://rajpurkar.github.io/SQuAD-explorer) dataset for 3 epochs.
 
 The fine-tuning process was performed on a single P100 GPUs (16GB). The hyperparameters are:
 
@@ -23,6 +29,4 @@ although Bioformer was pretrained only on biomedical texts.
 
 
 ## Speed
-In our experiments, the inference speed of Bioformer is 3x as fast as BERT-base/BioBERT/PubMedBERT, and is 40% faster than DistilBERT. 
-
-
+In our experiments, the inference speed of Bioformer is 3x as fast as BERT-base/BioBERT/PubMedBERT, and is 40% faster than DistilBERT.