{"adoption": {"forks": 139, "observed_at": "2026-08-28T04:03:21.940657+00:00", "stars": 1047}, "canonical_url": "https://ross.abutalabs.com/products/distillkit", "card": {"archived": false, "artifact_type": "library", "description": "An Open Source Toolkit For LLM Distillation", "domain": ["large-language-models", "machine-learning", "deep-learning"], "enriched": true, "function": ["llm-training", "machine-learning", "deep-learning", "gpu-computing"], "health_score": 69, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["arcee-ai/DistillKit"], "name": "arcee-ai/DistillKit", "platform": ["python"], "pushed_at": "2026-05-12T20:10:14+00:00", "repo": "arcee-ai/DistillKit", "stars": 1047, "tags": ["knowledge-distillation", "logit-compression", "huggingface", "teacher-student-training", "offline-distillation", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["distill a large teacher LLM into a smaller student model", "run offline distillation from pre-captured teacher logits", "compress teacher logit datasets for large-scale distillation", "train a student model with KL divergence and other distillation losses", "capture teacher model outputs for later distillation training"], "what_it_is": "DistillKit is an open-source Python toolkit for knowledge distillation of large language models, supporting both online and offline distillation workflows. It includes an advanced logit compression system (polynomial approximation, quantization, and bit-packing) that makes large-scale offline distillation practical.", "when_to_avoid": ["you need general-purpose LLM fine-tuning rather than distillation", "you want a no-code or fully managed training service", "you lack GPU resources for model training", "you need distillation for non-language modalities"], "when_to_choose": ["you need to distill an LLM at scale using pre-captured teacher outputs", "you want battle-tested tooling that has powered production model releases", "you want flexible, composable distillation loss functions", "you already use the HuggingFace Transformers/TRL/Accelerate ecosystem"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/distillkit", "repo": "arcee-ai/DistillKit", "role": "main", "score": 60}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.940657+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:01:05.060650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "93c6e0772ce7469e067ef23dbfaeafad1edde47e66c860b791cf8f29f47ff47e", "fetched_at": "2026-08-28T04:03:21.940657+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/DistillKit"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 82, "longevity": 54, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 763, "days_push": 113, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 60, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}