{"adoption": {"forks": 213, "observed_at": "2026-08-28T04:06:42.024097+00:00", "stars": 2375}, "canonical_url": "https://ross.abutalabs.com/products/large_concept_model", "card": {"archived": false, "artifact_type": "library", "description": "Large Concept Models: Language modeling in a sentence representation space", "domain": ["large-language-models", "machine-learning"], "enriched": true, "function": ["machine-learning", "deep-learning", "nlp", "llm-training"], "health_score": 22, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "experimental", "member_repos": ["facebookresearch/large_concept_model"], "name": "facebookresearch/large_concept_model", "platform": ["python"], "pushed_at": "2025-01-29T05:57:33+00:00", "repo": "facebookresearch/large_concept_model", "stars": 2375, "tags": ["language-models", "seq2seq", "sentence-embeddings", "sonar", "fairseq2", "pytorch", "diffusion", "research-code", "natural-language-processing", "research", "linux", "gpu"], "topics": ["language-models", "nlp", "pytorch", "seq2seq", "sequence-to-sequence"], "urls": [], "use_cases": ["train a large concept model on sentence embeddings", "reproduce the LCM paper experiments", "generate text sentence-by-sentence in a multilingual embedding space", "experiment with diffusion-based sequence generation in SONAR space", "finetune a 1.6B concept model", "research language modeling beyond token-level prediction"], "what_it_is": "Official PyTorch implementation of Meta's Large Concept Models (LCM), which perform language modeling by autoregressively predicting sentences in the SONAR sentence embedding space rather than at the token level. It includes training and finetuning recipes for 1.6B parameter MSE-regression and two-tower diffusion variants.", "when_to_avoid": ["you need a production-ready LLM for chat or inference", "you want a plug-and-play library rather than research code", "you cannot set up fairseq2 and GPU dependencies yourself"], "when_to_choose": ["you want to experiment with or reproduce Meta's Large Concept Model research", "you need sentence-level autoregressive generation in a multilingual embedding space", "you are researching alternatives to token-level language modeling"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/large_concept_model", "repo": "facebookresearch/large_concept_model", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:42.024097+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:35:02.990490+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5c25ff0eb1cf2baa4edf894404b5bbacb8013c2ae60440b8fefbea55f77acbaa", "fetched_at": "2026-08-28T04:06:42.024097+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/large_concept_model"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 4, "longevity": 44, "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": 629, "days_push": 581, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}