Task
Fill Mask
G
microsoft/graphcodebert-base
Fill Mask·microsoft· 951.8K· 90
transformers
arxiv:2009.08366deploy:azureregion:us
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 func
# pull & run locally
pip install mlforge-sdk && mlforge pull microsoft/graphcodebert-base
pip install mlforge-sdk && mlforge pull microsoft/graphcodebert-base
Model details
Provider
microsoft
Framework
transformers
Size
3.5 GB
Downloads
951.8K
Likes
90
Paper
arXiv:2009.08366
Updated
2022-09-26
About microsoft/graphcodebert-base
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.