# microsoft/CodeBERT

CodeBERT

Repository: https://github.com/microsoft/CodeBERT
Canonical: https://ross.abutalabs.com/products/codebert
Language: Python
License: MIT
License Family: permissive
Last push: 2023-07-09T12:26:30+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2268, "days_push": 1151, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2785, forks 497 (observed 2026-08-28T04:07:21.906750+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp, search-engine
- domain: machine-learning, developer-tools, programming-languages
- platform: python, cross-platform
- tags: codebert, pretrained-model, code-search, transformers, huggingface, code-embeddings, research, natural-language-processing, gpu

## Member repositories
- microsoft/CodeBERT (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:21.906750+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:16:02.446701+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/CodeBERT (fetched 2026-08-28T04:07:21.906750+00:00, sha 0d5c99293026)
- Data as of 2026-08-30T08:39:29.467469+00:00.