{"adoption": {"forks": 497, "observed_at": "2026-08-28T04:07:21.906750+00:00", "stars": 2785}, "canonical_url": "https://ross.abutalabs.com/products/codebert", "card": {"archived": false, "artifact_type": "library", "description": "CodeBERT", "domain": ["machine-learning", "developer-tools", "programming-languages"], "enriched": true, "function": ["machine-learning", "deep-learning", "nlp", "search-engine"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["microsoft/CodeBERT"], "name": "microsoft/CodeBERT", "platform": ["python", "cross-platform"], "pushed_at": "2023-07-09T12:26:30+00:00", "repo": "microsoft/CodeBERT", "stars": 2785, "tags": ["codebert", "pretrained-model", "code-search", "transformers", "huggingface", "code-embeddings", "research", "natural-language-processing", "gpu"], "topics": [], "urls": [], "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"], "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.", "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"], "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"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/codebert", "repo": "microsoft/CodeBERT", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.906750+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T08:16:02.446701+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0d5c992930267f8b0e035624cfc2b3b1c4258ccda8eca521dc7d4fe417155323", "fetched_at": "2026-08-28T04:07:21.906750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/CodeBERT"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2268, "days_push": 1151, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}