{"adoption": {"forks": 18, "observed_at": "2026-08-28T04:07:22.345881+00:00", "stars": 2796}, "canonical_url": "https://ross.abutalabs.com/products/yayi2", "card": {"archived": true, "artifact_type": "learning-resource", "description": "YAYI 2 是中科闻歌研发的新一代开源大语言模型，采用了超过 2 万亿 Tokens 的高质量、多语言语料进行预训练。(Repo for YaYi 2 Chinese LLMs)", "domain": ["large-language-models", "artificial-intelligence"], "enriched": true, "function": ["llm-inference", "llm-training", "chatbot"], "health_score": 10, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["wenge-research/YAYI2"], "name": "wenge-research/YAYI2", "platform": ["python"], "pushed_at": "2024-04-07T08:27:39+00:00", "repo": "wenge-research/YAYI2", "stars": 2796, "tags": ["chinese-llm", "pretrained-language-model", "30b", "multilingual", "huggingface", "model-weights", "lora-finetuning", "natural-language-processing", "gpu", "linux"], "topics": ["artificial-intelligence", "chat", "chinese", "gpt", "natural-language-generation", "pretrained-language-model", "yayi"], "urls": [], "use_cases": ["run a chinese open-source llm locally", "download pretrained 30b language model weights", "finetune a chinese llm with lora", "chat with a chinese gpt-style model", "get multilingual llm pretraining data", "evaluate llm on c-eval and mmlu benchmarks"], "what_it_is": "YAYI 2 is a family of open-source multilingual large language models (30B Base and Chat variants) developed by Wenge Research, pretrained on over 2 trillion tokens with a focus on Chinese. The repository provides model weights, inference code, fine-tuning scripts (full-parameter and LoRA), and a 500GB pretraining dataset.", "when_to_avoid": ["you need a small model that runs on consumer hardware", "you require the Chat variant, which was not fully released at last update", "you need a commercially permissive model license (model weights use a custom YAYI license, data is CC BY-NC 4.0)"], "when_to_choose": ["you need a strong open-source Chinese-language LLM with permissive Apache-2.0 code licensing", "you want to fine-tune a 30B model with provided LoRA or full-parameter training scripts", "you need multilingual pretraining data for LLM research"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/yayi2", "repo": "wenge-research/YAYI2", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:22.345881+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T08:14:39.956966+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d551f53b4a8f04640aa9762592d6c95be4679f91d910109f50eddda0acccda94", "fetched_at": "2026-08-28T04:07:22.345881+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wenge-research/YAYI2"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 70, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 992, "days_push": 878, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}