{"adoption": {"forks": 229, "observed_at": "2026-08-28T04:05:00.191120+00:00", "stars": 1538}, "canonical_url": "https://ross.abutalabs.com/products/vilt", "card": {"archived": false, "artifact_type": "library", "description": "Code for the ICML 2021 (long talk) paper: \"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision\"", "domain": ["artificial-intelligence", "machine-learning", "computer-vision"], "enriched": true, "function": ["machine-learning", "deep-learning", "nlp", "image-processing"], "health_score": 20, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["dandelin/ViLT"], "name": "dandelin/ViLT", "platform": ["python"], "pushed_at": "2024-04-03T02:07:24+00:00", "repo": "dandelin/ViLT", "stars": 1538, "tags": ["vision-and-language", "transformer", "vqa", "visual-question-answering", "image-text-retrieval", "masked-language-modeling", "pretrained-models", "research-code", "natural-language-processing", "gpu"], "topics": ["vision-and-language"], "urls": [], "use_cases": ["run visual question answering on images", "answer questions about an image with a pretrained model", "retrieve images from text descriptions", "finetune a vision-language transformer on my own dataset", "reproduce the ViLT paper results", "visualize masked language model attention over images"], "what_it_is": "Official PyTorch code for the ICML 2021 paper ViLT, a vision-and-language transformer that performs multimodal pre-training without convolutional image feature extractors or region supervision. It ships pretrained checkpoints and finetuned models for VQA, NLVR2, and image-text retrieval, plus Gradio demos.", "when_to_avoid": ["you need production-grade multimodal APIs with active support", "you want the latest state-of-the-art vision-language models", "you need a maintained library rather than research code"], "when_to_choose": ["you need a lightweight multimodal transformer without heavy object-detection feature extraction", "you want pretrained VQA or image-text retrieval models for research", "you want to reproduce or extend the ViLT paper"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/vilt", "repo": "dandelin/ViLT", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:00.191120+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:30:57.096307+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e244820d32ac047cc77f0359f4be6b83acfb48a30ec52ec5cc58af9af2932e22", "fetched_at": "2026-08-28T04:05:00.191120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dandelin/ViLT"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "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": 1987, "days_push": 883, "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}}