Update README.md

README.md

@@ -1,6 +1,17 @@
+---
+arxiv: 2009.08366
+language:
+- code
+license: mit
+---
 
+This is an *unofficial* reupload of [microsoft/graphcodebert-base](https://huggingface.co/microsoft/graphcodebert-base) in the `SafeTensors` format using `transformers` `4.40.1`. The goal of this reupload is to prevent older models that are still relevant baselines from becoming stale as a result of changes in HuggingFace. Additionally, I may include minor corrections, such as model max length configuration.
 
-This is an *unofficial* reupload of [microsoft/graphcodebert-base](https://huggingface.co/microsoft/graphcodebert-base) in the `SafeTensors` format using `transformers` `4.40.1`. The goal of this reupload is to prevent older models that are still relevant baselines from becoming stale as a result of changes in HuggingFace. Additionally, I may include minor corrections, such as model max length configuration.## GraphCodeBERT model
+Original model card below:
+
+---
+
+## GraphCodeBERT model
 
 GraphCodeBERT is a graph-based pre-trained model based on the Transformer architecture for programming language, which also considers data-flow information along with code sequences. GraphCodeBERT consists of 12 layers, 768 dimensional hidden states, and 12 attention heads. The maximum sequence length for the model is 512. The model is trained on the CodeSearchNet dataset, which includes 2.3M functions with document pairs for six programming languages.