{"adoption": {"forks": 287, "observed_at": "2026-08-28T04:07:45.796690+00:00", "stars": 3139}, "canonical_url": "https://ross.abutalabs.com/products/video-llama", "card": {"archived": false, "artifact_type": "library", "description": "[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding", "domain": ["large-language-models", "computer-vision", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "deep-learning", "llm-inference", "video-processing", "audio-processing", "chatbot"], "health_score": 20, "homepage": null, "language": "Python", "license": "BSD-3-Clause", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["DAMO-NLP-SG/Video-LLaMA"], "name": "DAMO-NLP-SG/Video-LLaMA", "platform": ["python"], "pushed_at": "2024-06-04T07:06:41+00:00", "repo": "DAMO-NLP-SG/Video-LLaMA", "stars": 3139, "tags": ["multimodal", "video-understanding", "audio-visual", "instruction-tuning", "llama", "blip2", "vision-language-model", "research-model", "video", "natural-language-processing", "gpu", "linux"], "topics": ["large-language-models", "video-language-pretraining", "vision-language-pretraining", "blip2", "llama", "minigpt4", "cross-modal-pretraining", "multi-modal-chatgpt"], "urls": [], "use_cases": ["chat with a video using an LLM", "understand video content with a multimodal model", "ask questions about a video's audio and visuals", "build a video question-answering demo", "finetune a video-language model on custom data", "summarize videos with a large language model"], "what_it_is": "Video-LLaMA is an instruction-tuned audio-visual language model that extends LLaMA with video and audio understanding via cross-modal pretraining (BLIP-2 style Q-former). It provides pretrained and finetuned checkpoints plus inference code for multimodal video chat.", "when_to_avoid": ["you need the strongest or easiest-to-use codebase - the authors recommend VideoLLaMA2", "you need production-grade, actively maintained software", "you lack GPU resources for 7B/13B multimodal inference", "you need Chinese-language chat support"], "when_to_choose": ["you need open checkpoints for video+audio instruction-following chat", "you want a research baseline for video-language understanding", "you want to customize a pretrained video LLM with your own data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/video-llama", "repo": "DAMO-NLP-SG/Video-LLaMA", "role": "main", "score": 29}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:45.796690+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:26:02.867502+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "de85c22c827a0f2680917809a477f6415a785be2ce9df4e3980c6cabfb1608c6", "fetched_at": "2026-08-28T04:07:45.796690+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DAMO-NLP-SG/Video-LLaMA"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 86, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1215, "days_push": 820, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 29, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}