{"adoption": {"forks": 97, "observed_at": "2026-08-28T04:03:56.169545+00:00", "stars": 1191}, "canonical_url": "https://ross.abutalabs.com/products/chat-dataset-baseline", "card": {"archived": false, "artifact_type": "dataset", "description": "人工精调的中文对话数据集和一段chatglm的微调代码", "domain": ["large-language-models", "machine-learning"], "enriched": true, "function": ["machine-learning", "llm-training", "data-generation"], "health_score": 32, "homepage": null, "language": "Jupyter Notebook", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["hikariming/chat-dataset-baseline"], "name": "hikariming/chat-dataset-baseline", "platform": ["python"], "pushed_at": "2025-05-03T02:36:56+00:00", "repo": "hikariming/chat-dataset-baseline", "stars": 1191, "tags": ["chinese-dataset", "chatglm", "alpaca", "sft", "lora", "llama-factory", "fine-tuning", "natural-language-processing"], "topics": ["alpaca", "chatglm", "dataset"], "urls": [], "use_cases": ["fine-tune a Chinese chat model", "get a curated Chinese instruction dataset", "train ChatGLM with LoRA", "create a custom Chinese assistant baseline", "translate and adapt alpaca-style data for Chinese"], "what_it_is": "A curated Chinese conversational dataset plus fine-tuning scripts for training chat models like ChatGLM, built on top of LLaMA-Factory. It includes preprocessing code to customize model identity and training scripts for LoRA or full-parameter SFT.", "when_to_avoid": ["You need English or multilingual datasets", "You want an actively maintained project (author recommends LLaMA-Factory instead)", "You need a licensed dataset (no license specified)"], "when_to_choose": ["You want a ready-made Chinese dialogue dataset for SFT", "You use LLaMA-Factory and want drop-in data and training scripts", "You need a base Chinese chat model to further customize for a domain"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/chat-dataset-baseline", "repo": "hikariming/chat-dataset-baseline", "role": "main", "score": 39}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:56.169545+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:22:42.332573+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c05478f7589b4b05e73291cc952a594182c9d985c664117cf4ceae644351a0cd", "fetched_at": "2026-08-28T04:03:56.169545+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hikariming/chat-dataset-baseline"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 19, "longevity": 90, "rhythm": 35}, "computed_at": "2026-09-03T02:39:23.370411+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": 1265, "days_push": 488, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 39, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}