{"adoption": {"forks": 94, "observed_at": "2026-08-28T04:03:16.740356+00:00", "stars": 1026}, "canonical_url": "https://ross.abutalabs.com/products/llama-2-onnx", "card": {"archived": false, "artifact_type": "library", "description": null, "domain": ["large-language-models", "machine-learning", "developer-tools"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["microsoft/Llama-2-Onnx"], "name": "microsoft/Llama-2-Onnx", "platform": ["python", "cross-platform"], "pushed_at": "2024-01-04T00:46:46+00:00", "repo": "microsoft/Llama-2-Onnx", "stars": 1026, "tags": ["onnx", "llama-2", "model-optimization", "inference", "microsoft"], "topics": [], "urls": [], "use_cases": ["run llama 2 with onnx runtime", "convert llama 2 to onnx format", "text generation with llama 2 on cpu or gpu", "deploy llama 2 without pytorch", "try llama 2 inference examples", "benchmark llama 2 onnx performance"], "what_it_is": "Microsoft's optimized ONNX export of Meta's Llama 2 models (7B and 13B, pretrained and fine-tuned, float16/float32), distributed via Git submodules with example code for running inference. It enables running Llama 2 with ONNX Runtime instead of the original PyTorch weights.", "when_to_avoid": ["you need other LLMs than Llama 2", "you want to fine-tune or train models rather than run inference", "you cannot accept the gated access and Llama Community License restrictions", "you need the latest models like Llama 3"], "when_to_choose": ["you want to run Llama 2 using ONNX Runtime for optimized inference", "you need pretrained or fine-tuned 7B/13B Llama 2 weights in ONNX format", "you want a minimal example of LLM text completion with ONNX"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llama-2-onnx", "repo": "microsoft/Llama-2-Onnx", "role": "main", "score": 28}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:16.740356+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:07:58.976041+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8a33d314d8aa949b1ed8b1b3fda9ca49efc5a2ba446d99f8cf5182b76373b1ce", "fetched_at": "2026-08-28T04:03:16.740356+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/Llama-2-Onnx"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 81, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1143, "days_push": 973, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 28, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}