AI Model Catalog | Microsoft Foundry Models

microsoft-codebert-base-mlm

Version: 8

HuggingFace•Last updated July 2025

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.

Usage

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)
print(outputs)

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}

Reference

Bimodal CodeBERT trained with MLM+RTD objective (suitable for code search and document generation)
🤗 Hugging Face's CodeBERTa (small size, 6 layers)

Citation

@misc{feng2020codebert,
    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},
    year={2020},
    eprint={2002.08155},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

microsoft/codebert-base-mlm powered by Hugging Face Inference Toolkit

Send Request

You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: application/json" \
    -d '{"inputs":"The answer to the universe is undefined."}'

Supported Parameters

inputs (string): The text with masked tokens
parameters (object):
- top_k (integer): When passed, overrides the number of predictions to return.
- targets (string[]): When passed, the model will limit the scores to the passed targets instead of looking up in the whole vocabulary. If the provided targets are not in the model vocab, they will be tokenized and the first resulting token will be used (with a warning, and that might be slower).

Check the full API Specification at the Hugging Face Inference documentation .

Model Specifications

LicenseUnknown

Last UpdatedJuly 2025

ProviderHuggingFace

Quick Start