[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TPYNER1TRA97SJZ7PYWNZ":3,"skill-same:01M78TPYNER1TRA97SJZ7PYWNZ":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78TPYNER1TRA97SJZ7PYWNZ","chinese-bert-wwm",null,"Route Chinese-BERT-wwm model loading, model selection, benchmark data, and troubleshooting workflows for HFL Chinese BERT-family resources.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchinese-bert-wwm\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: chinese-bert-wwm\ndescription: \"Route Chinese-BERT-wwm model loading, model selection, benchmark\n  data, and troubleshooting workflows for HFL Chinese BERT-family resources.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Chinese-BERT-wwm\n\nUse this repo skill when a task involves HFL Chinese BERT\u002FRoBERTa\u002FRBT checkpoints released from the Chinese-BERT-wwm resource repository, Chinese Whole Word Masking (WWM), model loading through Transformers or PaddleHub, downstream Chinese NLP benchmark interpretation, or the bundled sentiment\u002FNER dataset schemas.\n\n## What this skill covers\n\n- HFL model ids such as `hfl\u002Fchinese-bert-wwm`, `hfl\u002Fchinese-bert-wwm-ext`, `hfl\u002Fchinese-roberta-wwm-ext`, `hfl\u002Fchinese-roberta-wwm-ext-large`, `hfl\u002Frbt3`, `hfl\u002Frbt4`, `hfl\u002Frbt6`, and `hfl\u002Frbtl3`.\n- Correct Transformers class choice: use `BertTokenizer`\u002F`BertModel` or `AutoTokenizer`\u002F`AutoModel`; do not use RoBERTa classes for the RoBERTa-wwm-named checkpoints.\n- Offline\u002Fcache-aware model-id validation and optional online checkpoint loading decisions.\n- Model selection and fine-tuning expectations for Chinese reading comprehension, sentiment, sentence-pair matching, NLI, document classification, and Traditional Chinese tasks.\n- Dataset source pointers, copyright\u002Fdownload constraints, benchmark metrics, and schema validation for included ChnSentiCorp, Weibo, and PeopleDaily fixture archives.\n\n## First steps\n\n1. Read `references\u002Fmodel-family-overview.md` for the compact model catalog, WWM meaning, and route map.\n2. If the task is about loading a checkpoint or validating a model id\u002Fcache, open `sub-skills\u002Fmodel-loading\u002FSKILL.md`.\n3. If the task is about choosing a model, learning rates, compact variants, WWM\u002FCWS implications, or reproduction expectations, open `sub-skills\u002Ftask-selection-and-finetuning\u002FSKILL.md`.\n4. If the task is about datasets, benchmark metrics, included zip schemas, or missing\u002Fcopyright-restricted data, open `sub-skills\u002Fdata-and-benchmarks\u002FSKILL.md`.\n5. For setup failures that span multiple workflows, open `references\u002Ftroubleshooting.md`.\n\n## Sub-skill routes\n\n| User task | Read |\n| --- | --- |\n| \"Load `hfl\u002Fchinese-roberta-wwm-ext` with Transformers\", \"is `RobertaTokenizer` correct?\", \"check offline cache for `hfl\u002Frbt3`\", \"what PaddleHub module name should I use?\" | `sub-skills\u002Fmodel-loading\u002FSKILL.md` |\n| \"Which checkpoint should I fine-tune for CMRC\u002FDRCD\u002FXNLI\u002FLCQMC?\", \"what LR did the README use?\", \"do I need Chinese word segmentation for WWM?\", \"should I use RBTL3 or truncate a large model?\" | `sub-skills\u002Ftask-selection-and-finetuning\u002FSKILL.md` |\n| \"Where is BQ Corpus\u002FLCQMC data?\", \"validate `chnsenticorp.zip`\", \"what metric does DRCD use?\", \"is CJRC test data official?\" | `sub-skills\u002Fdata-and-benchmarks\u002FSKILL.md` |\n\n## Minimal setup check\n\nThis repository is not an installable Python package. Transformers workflows require an environment with `transformers` and, for full model materialization, a backend such as PyTorch. In the user's chosen Python environment, a typical public setup is:\n\n```bash\npython -m pip install transformers torch\n```\n\nThe root helper performs an offline import\u002Fmodel-id check and never downloads checkpoints:\n\n```bash\npython scripts\u002Fcheck_chinese_bert_wwm_setup.py --help\npython scripts\u002Fcheck_chinese_bert_wwm_setup.py --require-transformers\npython scripts\u002Fcheck_chinese_bert_wwm_setup.py --list-models\n```\n\nFor model-specific cache\u002Fload checks, use `sub-skills\u002Fmodel-loading\u002Fscripts\u002Fcheck_transformers_model.py`. For included dataset archive schemas, use `sub-skills\u002Fdata-and-benchmarks\u002Fscripts\u002Fvalidate_dataset_schema.py`.\n\n## Key operating facts\n\n- WWM is a pretraining data-construction strategy. It does not require manual word segmentation of downstream input text.\n- The RoBERTa-wwm-ext models are RoBERTa-like BERT-family models. Load them as BERT models or through `Auto*` classes.\n- TensorFlow checkpoint zip downloads and Hugging Face\u002FPyTorch model directories are different file formats; choose the loading\u002Fconversion path explicitly.\n- Published benchmark values are empirical references, often max\u002Faverage over multiple runs, not guaranteed reproduction targets.\n- Some dataset folders provide only source pointers due to copyright, large file size, or in-house test constraints. Do not create downloaders that bypass those constraints.\n\n## Required references\n\n- `references\u002Frepo-provenance.md`: source commit, evidence paths, package\u002Flibrary context, and refresh baseline.\n- `references\u002Frepo-routing-metadata.json`: structured scenario metadata used if this verified skill is later imported into the managed repo-skill library.\n- `references\u002Fmodel-family-overview.md`: shared model catalog and route map.\n- `references\u002Ftroubleshooting.md`: cross-cutting environment, cache, dataset, and reproducibility failures.\n\n## Boundaries\n\nThis skill does not provide the unreleased original pretraining implementation, full model weights, full dataset downloads, PaddleHub\u002FPaddlePaddle as required dependencies, or guaranteed benchmark reproduction. Ask for user approval before downloading large checkpoints, installing broad optional frameworks, using credentials, mutating caches, or redistributing restricted datasets.\n","# Chinese-BERT-wwm\n\nUse this repo skill when a task involves HFL Chinese BERT\u002FRoBERTa\u002FRBT checkpoints released from the Chinese-BERT-wwm resource repository, Chinese Whole Word Masking (WWM), model loading through Transformers or PaddleHub, downstream Chinese NLP benchmark interpretation, or the bundled sentiment\u002FNER dataset schemas.\n\n## What this skill covers\n\n- HFL model ids such as `hfl\u002Fchinese-bert-wwm`, `hfl\u002Fchinese-bert-wwm-ext`, `hfl\u002Fchinese-roberta-wwm-ext`, `hfl\u002Fchinese-roberta-wwm-ext-large`, `hfl\u002Frbt3`, `hfl\u002Frbt4`, `hfl\u002Frbt6`, and `hfl\u002Frbtl3`.\n- Correct Transformers class choice: use `BertTokenizer`\u002F`BertModel` or `AutoTokenizer`\u002F`AutoModel`; do not use RoBERTa classes for the RoBERTa-wwm-named checkpoints.\n- Offline\u002Fcache-aware model-id validation and optional online checkpoint loading decisions.\n- Model selection and fine-tuning expectations for Chinese reading comprehension, sentiment, sentence-pair matching, NLI, document classification, and Traditional Chinese tasks.\n- Dataset source pointers, copyright\u002Fdownload constraints, benchmark metrics, and schema validation for included ChnSentiCorp, Weibo, and PeopleDaily fixture archives.\n\n## First steps\n\n1. Read `references\u002Fmodel-family-overview.md` for the compact model catalog, WWM meaning, and route map.\n2. If the task is about loading a checkpoint or validating a model id\u002Fcache, open `sub-skills\u002Fmodel-loading\u002FSKILL.md`.\n3. If the task is about choosing a model, learning rates, compact variants, WWM\u002FCWS implications, or reproduction expectations, open `sub-skills\u002Ftask-selection-and-finetuning\u002FSKILL.md`.\n4. If the task is about datasets, benchmark metrics, included zip schemas, or missing\u002Fcopyright-restricted data, open `sub-skills\u002Fdata-and-benchmarks\u002FSKILL.md`.\n5. For setup failures that span multiple workflows, open `references\u002Ftroubleshooting.md`.\n\n## Sub-skill routes\n\n| User task | Read |\n| --- | --- |\n| \"Load `hfl\u002Fchinese-roberta-wwm-ext` with Transformers\", \"is `RobertaTokenizer` correct?\", \"check offline cache for `hfl\u002Frbt3`\", \"what PaddleHub module name should I use?\" | `sub-skills\u002Fmodel-loading\u002FSKILL.md` |\n| \"Which checkpoint should I fine-tune for CMRC\u002FDRCD\u002FXNLI\u002FLCQMC?\", \"what LR did the README use?\", \"do I need Chinese word segmentation for WWM?\", \"should I use RBTL3 or truncate a large model?\" | `sub-skills\u002Ftask-selection-and-finetuning\u002FSKILL.md` |\n| \"Where is BQ Corpus\u002FLCQMC data?\", \"validate `chnsenticorp.zip`\", \"what metric does DRCD use?\", \"is CJRC test data official?\" | `sub-skills\u002Fdata-and-benchmarks\u002FSKILL.md` |\n\n## Minimal setup check\n\nThis repository is not an installable Python package. Transformers workflows require an environment with `transformers` and, for full model materialization, a backend such as PyTorch. In the user's chosen Python environment, a typical public setup is:\n\n```bash\npython -m pip install transformers torch\n```\n\nThe root helper performs an offline import\u002Fmodel-id check and never downloads checkpoints:\n\n```bash\npython scripts\u002Fcheck_chinese_bert_wwm_setup.py --help\npython scripts\u002Fcheck_chinese_bert_wwm_setup.py --require-transformers\npython scripts\u002Fcheck_chinese_bert_wwm_setup.py --list-models\n```\n\nFor model-specific cache\u002Fload checks, use `sub-skills\u002Fmodel-loading\u002Fscripts\u002Fcheck_transformers_model.py`. For included dataset archive schemas, use `sub-skills\u002Fdata-and-benchmarks\u002Fscripts\u002Fvalidate_dataset_schema.py`.\n\n## Key operating facts\n\n- WWM is a pretraining data-construction strategy. It does not require manual word segmentation of downstream input text.\n- The RoBERTa-wwm-ext models are RoBERTa-like BERT-family models. Load them as BERT models or through `Auto*` classes.\n- TensorFlow checkpoint zip downloads and Hugging Face\u002FPyTorch model directories are different file formats; choose the loading\u002Fconversion path explicitly.\n- Published benchmark values are empirical references, often max\u002Faverage over multiple runs, not guaranteed reproduction targets.\n- Some dataset folders provide only source pointers due to copyright, large file size, or in-house test constraints. Do not create downloaders that bypass those constraints.\n\n## Required references\n\n- `references\u002Frepo-provenance.md`: source commit, evidence paths, package\u002Flibrary context, and refresh baseline.\n- `references\u002Frepo-routing-metadata.json`: structured scenario metadata used if this verified skill is later imported into the managed repo-skill library.\n- `references\u002Fmodel-family-overview.md`: shared model catalog and route map.\n- `references\u002Ftroubleshooting.md`: cross-cutting environment, cache, dataset, and reproducibility failures.\n\n## Boundaries\n\nThis skill does not provide the unreleased original pretraining implementation, full model weights, full dataset downloads, PaddleHub\u002FPaddlePaddle as required dependencies, or guaranteed benchmark reproduction. Ask for user approval before downloading large checkpoints, installing broad optional frameworks, using credentials, mutating caches, or redistributing restricted datasets.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fchinese-bert-wwm",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill chinese-bert-wwm",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill chinese-bert-wwm",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill chinese-bert-wwm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchinese-bert-wwm\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fmodel-family-overview.md","REFERENCE","参考文档",4446,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchinese-bert-wwm\u002Freferences\u002Fmodel-family-overview.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",2668,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchinese-bert-wwm\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",458,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchinese-bert-wwm\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",5356,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchinese-bert-wwm\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_chinese_bert_wwm_setup.py","SCRIPT","脚本",5222,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchinese-bert-wwm\u002Fscripts\u002Fcheck_chinese_bert_wwm_setup.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]