{"adoption": {"forks": 174, "observed_at": "2026-08-28T04:05:28.793331+00:00", "stars": 1732}, "canonical_url": "https://ross.abutalabs.com/products/multimodal", "card": {"archived": false, "artifact_type": "library", "description": "TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.", "domain": ["machine-learning", "deep-learning", "artificial-intelligence", "computer-vision"], "enriched": true, "function": ["machine-learning", "deep-learning", "llm-training"], "health_score": 80, "homepage": null, "language": "Python", "license": "BSD-3-Clause", "license_family": "permissive", "maturity": "active", "member_repos": ["facebookresearch/multimodal"], "name": "facebookresearch/multimodal", "platform": ["python"], "pushed_at": "2026-08-24T15:05:20+00:00", "repo": "facebookresearch/multimodal", "stars": 1732, "tags": ["pytorch", "multimodal", "vision-language", "diffusion-models", "pretrained-models", "research", "natural-language-processing", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["train a multimodal vision-language model at scale", "fine-tune CLIP or FLAVA on my own dataset", "replicate BLIP-2 or CoCa research baselines in PyTorch", "build a text-to-image diffusion model like DALL-E 2", "get pretrained weights for multimodal models", "train an audio MAE model", "compose custom fusion layers and losses for multi-task learning"], "what_it_is": "TorchMultimodal is a PyTorch library from Meta for training state-of-the-art multimodal multi-task models at scale, covering both content understanding and generative models. It provides modular building blocks (fusion layers, losses, datasets), pretrained model classes like CLIP, FLAVA, BLIP-2, and DALL-E 2, and example scripts replicating published research baselines.", "when_to_avoid": ["you need a production inference API rather than a research training library", "you want a framework-agnostic or non-PyTorch solution", "you need a stable, fully supported product rather than a beta research library"], "when_to_choose": ["you want PyTorch-native implementations of state-of-the-art multimodal models with pretrained weights", "you need modular, composable building blocks for multimodal research", "you want scalable training baselines for vision-language or generative multimodal tasks"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/multimodal", "repo": "facebookresearch/multimodal", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.793331+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:31:30.495928+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d67eb68a5bde988f15e8c19e02e0476675eccc651a66246c7afe4956d0c43262", "fetched_at": "2026-08-28T04:05:28.793331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/multimodal"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "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": 1679, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}