microsoft/CodeBERT

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2785 stars · 497 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A collection of pre-trained code models from Microsoft, including CodeBERT and successors like GraphCodeBERT and UniXcoder, usable via Hugging Face transformers. It provides embeddings and representations for programming languages and natural language pairs across six languages.

Use cases

• embed code and natural language into shared vectors
• build semantic code search over repositories
• find code snippets from natural language queries
• fine-tune a model for code understanding tasks
• clone detection and code classification experiments
• reproduce CodeBERT paper experiments

When to choose

• you need NL-to-code embeddings with a RoBERTa-compatible model
• you want a well-cited research baseline for code intelligence tasks
• you already use huggingface/transformers and want a drop-in code model

When to avoid

• you need a modern instruction-tuned code LLM for generation
• you need active development or recent updates
• you need long-context code understanding beyond LongCoder's limits

Facets

library · maturity maintenance

machine-learning deep-learning nlp search-engine machine-learning developer-tools programming-languages python cross-platform codebert pretrained-model code-search transformers huggingface code-embeddings research natural-language-processing gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/CodeBERT")