{"adoption": {"forks": 150, "observed_at": "2026-08-28T04:05:56.155002+00:00", "stars": 1930}, "canonical_url": "https://ross.abutalabs.com/products/hunyuanocr", "card": {"archived": false, "artifact_type": "library", "description": "HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better", "domain": ["computer-vision", "artificial-intelligence", "pdf"], "enriched": true, "function": ["ocr", "machine-learning", "llm-inference", "deep-learning"], "health_score": 77, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["Tencent-Hunyuan/HunyuanOCR"], "name": "Tencent-Hunyuan/HunyuanOCR", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-29T06:29:52+00:00", "repo": "Tencent-Hunyuan/HunyuanOCR", "stars": 1930, "tags": ["vision-language-model", "document-parsing", "speculative-decoding", "llama.cpp", "reinforcement-learning", "tencent-hunyuan", "table-parsing", "benchmarks", "natural-language-processing", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["extract text from images and scanned documents", "parse document layouts including tables", "run a fast lightweight OCR model on a PC", "translate text inside images", "benchmark OCR models for character-level hallucination", "fine-tune an OCR vision-language model with reinforcement learning"], "what_it_is": "HunyuanOCR-1.5 is a lightweight end-to-end OCR vision-language model from Tencent, with a unified inference environment, llama.cpp PC-side deployment, and a verl-based reinforcement learning training stack. It also ships related benchmarks such as CHAOS-Bench for character-level hallucination probing.", "when_to_avoid": ["you only need simple Tesseract-style text extraction without a GPU or VLM", "you need a fully permissive license (license is custom/NOASSERTION)", "you cannot run GPU inference or large model weights"], "when_to_choose": ["you need an open-source OCR VLM with document, table, and chart parsing", "you want lightweight on-device or PC-side OCR inference via llama.cpp", "you need a trainable OCR model with an RL training stack"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/hunyuanocr", "repo": "Tencent-Hunyuan/HunyuanOCR", "role": "main", "score": 59}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:56.155002+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:08:46.886792+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cceb7af4cfff0ec164738de5faa2ea4525a50f04bf3a0bad27ecc2b687254d2c", "fetched_at": "2026-08-28T04:05:56.155002+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Tencent-Hunyuan/HunyuanOCR"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 95, "longevity": 20, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+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": 288, "days_push": 35, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 59, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}