{"adoption": {"forks": 785, "observed_at": "2026-08-28T04:09:58.144500+00:00", "stars": 7310}, "canonical_url": "https://ross.abutalabs.com/products/mergekit", "card": {"archived": false, "artifact_type": "library", "description": "Tools for merging pretrained large language models.", "domain": ["large-language-models", "machine-learning", "deep-learning", "developer-tools"], "enriched": true, "function": ["machine-learning", "llm-training", "sdk", "cli"], "health_score": 88, "homepage": null, "language": "Python", "license": "LGPL-3.0", "license_family": "copyleft", "maturity": "active", "member_repos": ["arcee-ai/mergekit"], "name": "arcee-ai/mergekit", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-06-17T20:51:27+00:00", "repo": "arcee-ai/mergekit", "stars": 7310, "tags": ["model-merging", "llm", "model-fusion", "moe", "lora", "weight-space-merging", "huggingface", "gpu"], "topics": ["llama", "llm", "model-merging"], "urls": [], "use_cases": ["merge two fine-tuned llama models into one", "combine strengths of multiple LLMs without training", "create a mixture-of-experts model from existing checkpoints", "merge language models on a low-VRAM GPU", "extract a LoRA adapter from a merged model", "transfer capabilities between models without training data", "transplant tokenizer between language models"], "what_it_is": "mergekit is a Python toolkit for merging pre-trained large language models directly in weight space, supporting many merge methods (SLERP, TIES, DARE, MoE merging, evolutionary merges) with an out-of-core approach that runs on CPU or minimal GPU memory. It includes companion tools for LoRA extraction, raw PyTorch merging, tokenizer transplantation, and multi-stage merges.", "when_to_avoid": ["you need to train or fine-tune a model from scratch rather than merge existing ones", "your models have incompatible architectures or vastly different tokenizers without using the specialized tools", "you need a managed GUI service rather than a config-driven CLI toolkit"], "when_to_choose": ["you want to combine pretrained LLM checkpoints without additional training", "you have limited GPU memory and need out-of-core merging", "you want to experiment with many merge algorithms (SLERP, TIES, DARE, evolutionary)", "you work with Llama, Mistral, GPT-NeoX, or similar architectures"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mergekit", "repo": "arcee-ai/mergekit", "role": "main", "score": 63}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.144500+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:38:40.901404+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82676eda14f086b341bfc8cd27dbb4e46061c7c9f9289052570378d3fbc583a8", "fetched_at": "2026-08-28T04:09:58.144500+00:00", "kind": "readme", "missing": false, "url": "https://github.com/arcee-ai/mergekit"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 88, "longevity": 79, "rhythm": 22}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1108, "days_push": 77, "days_rel": 306, "gap_med": null, "n_releases_24m": 1}, "score": 63, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}