Add graphcodebert

Signed-off-by: Jael Gu <mengjia.gu@zilliz.com>

README.md

@@ -8,7 +8,8 @@
 
 A code search operator takes a text string of programming language or natural language as an input
 and returns an embedding vector in ndarray which captures the input's core semantic elements.
-This operator is implemented with pre-trained models from [Huggingface Transformers](https://huggingface.co/docs/transformers).
+This operator is implemented with pre-trained [CodeBert](https://arxiv.org/pdf/2002.08155.pdf) 
+or [GraphCodeBert](https://arxiv.org/abs/2009.08366) models from [Huggingface Transformers](https://huggingface.co/docs/transformers).
 
 <br />
 
@@ -64,7 +65,11 @@ The device to run model inference.
 The default value is None, which enables GPU if cuda is available.
 
 Supported model names:
-
+- huggingface/CodeBERTa-small-v1
+- microsoft/codebert-base
+- microsoft/codebert-base-mlm
+- mrm8488/codebert-base-finetuned-stackoverflow-ner
+- microsoft/graphcodebert-base
 
 <br />
 

codebert.py

@@ -143,7 +143,8 @@ class CodeBert(NNOperator):
             'huggingface/CodeBERTa-small-v1',
             'microsoft/codebert-base',
             'microsoft/codebert-base-mlm',
-            'mrm8488/codebert-base-finetuned-stackoverflow-ner'
+            'mrm8488/codebert-base-finetuned-stackoverflow-ner',
+            'microsoft/graphcodebert-base'
         ]
         full_list.sort()
         if format is None: