{"adoption": {"forks": 756, "observed_at": "2026-08-28T04:10:20.024621+00:00", "stars": 8275}, "canonical_url": "https://ross.abutalabs.com/products/belle", "card": {"archived": false, "artifact_type": "learning-resource", "description": "BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）", "domain": ["large-language-models", "machine-learning", "speech-processing"], "enriched": true, "function": ["llm-training", "machine-learning", "speech-recognition", "rag"], "health_score": 20, "homepage": null, "language": "HTML", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["LianjiaTech/BELLE"], "name": "LianjiaTech/BELLE", "platform": ["python"], "pushed_at": "2024-10-16T11:38:59+00:00", "repo": "LianjiaTech/BELLE", "stars": 8275, "tags": ["chinese-nlp", "instruction-tuning", "lora", "rlhf", "whisper", "multimodal", "open-models", "chatglm", "llama", "natural-language-processing", "gpu", "linux"], "topics": ["bloom", "instruction-set", "llama", "open-models", "gpt-q", "instruct-gpt", "gpt-evaluation", "chinese-nlp", "lora", "instruct-finetune"], "urls": [], "use_cases": ["fine-tune a Chinese instruction-following chatbot on an open LLM", "download Chinese instruction tuning datasets generated from ChatGPT", "train models with LoRA or RLHF (PPO/DPO) for Chinese dialogue", "improve Whisper speech recognition accuracy for Chinese audio", "explore multimodal Chinese vision-language models", "reduce the barrier to building custom Chinese LLMs"], "what_it_is": "BELLE is an open-source project providing Chinese-optimized instruction-tuned large language models, training data, and fine-tuning code built on open pretrained backbones like LLaMA and BLOOM. It also releases enhanced Chinese speech recognition models (fine-tuned Whisper) and multimodal variants, along with technical reports on training techniques.", "when_to_avoid": ["you need a production-ready hosted chat service rather than models and training code", "your focus is English-only or multilingual models beyond Chinese optimization", "you need actively cutting-edge releases, as updates have slowed since late 2024"], "when_to_choose": ["you need Chinese-language instruction-tuned models or training data", "you want open recipes for LoRA, full fine-tuning, or RLHF on Chinese LLMs", "you need Chinese-optimized speech recognition models", "you are researching how training data quality affects LLM performance"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/belle", "repo": "LianjiaTech/BELLE", "role": "main", "score": 21}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:20.024621+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:28:07.026401+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6c988e71350222429667da9b616b2cec66090bd352781bb745e395ff8d035f49", "fetched_at": "2026-08-28T04:10:20.024621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LianjiaTech/BELLE"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 90, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1265, "days_push": 686, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 21, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}