Back to all models
fill-mask mask_token: <mask>
Query this model
πŸ”₯ This model is currently loaded and running on the Inference API. ⚠️ This model could not be loaded by the inference API. ⚠️ This model can be loaded on the Inference API on-demand.
JSON Output
API endpoint  

⚑️ Upgrade your account to access the Inference API

Share Copied link to clipboard

Monthly model downloads

microsoft/codebert-base-mlm microsoft/codebert-base-mlm
last 30 days



Contributed by

Microsoft company
15 team members Β· 31 models

How to use this model directly from the πŸ€—/transformers library:

Copy to clipboard
from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("microsoft/codebert-base-mlm") model = AutoModelForMaskedLM.from_pretrained("microsoft/codebert-base-mlm")


Pretrained weights for CodeBERT: A Pre-Trained Model for Programming and Natural Languages.

Training Data

The model is trained on the code corpus of CodeSearchNet

Training Objective

This model is initialized with Roberta-base and trained with a simple MLM (Masked Language Model) objective.


from transformers import RobertaTokenizer, RobertaForMaskedLM, pipeline

model = RobertaForMaskedLM.from_pretrained('microsoft/codebert-base-mlm')
tokenizer = RobertaTokenizer.from_pretrained('microsoft/codebert-base-mlm')

code_example = "if (x is not None) <mask> (x>1)"
fill_mask = pipeline('fill-mask', model=model, tokenizer=tokenizer)

outputs = fill_mask(code_example)

Expected results:

{'sequence': '<s> if (x is not None) and (x>1)</s>', 'score': 0.6049249172210693, 'token': 8}
{'sequence': '<s> if (x is not None) or (x>1)</s>', 'score': 0.30680200457572937, 'token': 50}
{'sequence': '<s> if (x is not None) if (x>1)</s>', 'score': 0.02133703976869583, 'token': 114}
{'sequence': '<s> if (x is not None) then (x>1)</s>', 'score': 0.018607674166560173, 'token': 172}
{'sequence': '<s> if (x is not None) AND (x>1)</s>', 'score': 0.007619690150022507, 'token': 4248}


  1. Bimodal CodeBERT trained with MLM+RTD objective (suitable for code search and document generation)
  2. πŸ€— Hugging Face's CodeBERTa (small size, 6 layers)


    title={CodeBERT: A Pre-Trained Model for Programming and Natural Languages},
    author={Zhangyin Feng and Daya Guo and Duyu Tang and Nan Duan and Xiaocheng Feng and Ming Gong and Linjun Shou and Bing Qin and Ting Liu and Daxin Jiang and Ming Zhou},