[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZHX36TFH516JSGVTEENSK":3,"skill-same:01M78ZHX36TFH516JSGVTEENSK":74},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78ZHX36TFH516JSGVTEENSK","distillation-and-post-training",null,"MiniLLM, DPKD, and Tuna distillation and ranking-finetuning workflows for LMOps.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmops\u002Fsub-skills\u002Fdistillation-and-post-training\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: distillation-and-post-training\ndescription: \"MiniLLM, DPKD, and Tuna distillation and ranking-finetuning\n  workflows for LMOps.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Distillation and Post-Training\n\nUse this sub-skill for MiniLLM, DPKD, and Tuna workflows that distill or\nrank-finetune language models without entering VeRL-style experiential\nlearning.\n\n## Route here when\n\n- The task is MiniLLM SFT, KD, SeqKD, on-policy MiniLLM training, evaluation,\n  exposure-bias analysis, data processing, model resource planning, or tensor\n  parallel conversion.\n- The task is DPKD training or evaluation, including the runner scripts,\n  argument-group choices, DPO-style switches, and checkpoint\u002Foutput planning.\n- The task is Tuna probabilistic ranking or contextual ranking data\n  preparation, GPT-4 provenance checks, or ranking-aware finetuning.\n\n## Route away\n\n- GAD, OEL, OPCD, LLM-as-a-Coach, and OPO belong in\n  `..\u002Frl-experiential-learning\u002FSKILL.md`.\n- ResLoRA belongs in `..\u002Fadaptation-and-training\u002FSKILL.md`.\n\n## Bundled helpers\n\n- `scripts\u002Fmodel_parallel_conversion_plan.py` preflights checkpoint family,\n  source\u002Ftarget MP sizes, and path layout before any conversion.\n- `scripts\u002Fcheck_tuna_ranking_data.py` validates the minimal probabilistic and\n  contextual ranking JSON shapes used by Tuna.\n\n## Read next\n\n- `references\u002Fminillm-workflows.md`\n- `references\u002Fdpkd-workflows.md`\n- `references\u002Ftuna-data-and-training.md`\n- `references\u002Ftroubleshooting.md`\n\n## Working order\n\n1. Decide whether the request is MiniLLM, DPKD, or Tuna.\n2. Check the family reference and the bundled helper before any path-sensitive\n   or schema-sensitive action.\n3. Treat large model downloads, multi-node launches, and OpenAI-backed\n   ranking generation as documented workflow steps, not cheap smoke tests.\n4. If a failure looks like a shared LMOps issue, consult the parent skill's\n   broad project index when available at `..\u002F..\u002Freferences\u002Fproject-index.md`.\n","# Distillation and Post-Training\n\nUse this sub-skill for MiniLLM, DPKD, and Tuna workflows that distill or\nrank-finetune language models without entering VeRL-style experiential\nlearning.\n\n## Route here when\n\n- The task is MiniLLM SFT, KD, SeqKD, on-policy MiniLLM training, evaluation,\n  exposure-bias analysis, data processing, model resource planning, or tensor\n  parallel conversion.\n- The task is DPKD training or evaluation, including the runner scripts,\n  argument-group choices, DPO-style switches, and checkpoint\u002Foutput planning.\n- The task is Tuna probabilistic ranking or contextual ranking data\n  preparation, GPT-4 provenance checks, or ranking-aware finetuning.\n\n## Route away\n\n- GAD, OEL, OPCD, LLM-as-a-Coach, and OPO belong in\n  `..\u002Frl-experiential-learning\u002FSKILL.md`.\n- ResLoRA belongs in `..\u002Fadaptation-and-training\u002FSKILL.md`.\n\n## Bundled helpers\n\n- `scripts\u002Fmodel_parallel_conversion_plan.py` preflights checkpoint family,\n  source\u002Ftarget MP sizes, and path layout before any conversion.\n- `scripts\u002Fcheck_tuna_ranking_data.py` validates the minimal probabilistic and\n  contextual ranking JSON shapes used by Tuna.\n\n## Read next\n\n- `references\u002Fminillm-workflows.md`\n- `references\u002Fdpkd-workflows.md`\n- `references\u002Ftuna-data-and-training.md`\n- `references\u002Ftroubleshooting.md`\n\n## Working order\n\n1. Decide whether the request is MiniLLM, DPKD, or Tuna.\n2. Check the family reference and the bundled helper before any path-sensitive\n   or schema-sensitive action.\n3. Treat large model downloads, multi-node launches, and OpenAI-backed\n   ranking generation as documented workflow steps, not cheap smoke tests.\n4. If a failure looks like a shared LMOps issue, consult the parent skill's\n   broad project index when available at `..\u002F..\u002Freferences\u002Fproject-index.md`.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Flmops\u002Fsub-skills\u002Fdistillation-and-post-training",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill distillation-and-post-training",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill distillation-and-post-training",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill distillation-and-post-training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmops\u002Fsub-skills\u002Fdistillation-and-post-training\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdpkd-workflows.md","REFERENCE","参考文档",4575,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmops\u002Fsub-skills\u002Fdistillation-and-post-training\u002Freferences\u002Fdpkd-workflows.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fminillm-workflows.md",5020,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmops\u002Fsub-skills\u002Fdistillation-and-post-training\u002Freferences\u002Fminillm-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4508,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmops\u002Fsub-skills\u002Fdistillation-and-post-training\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftuna-data-and-training.md",4742,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmops\u002Fsub-skills\u002Fdistillation-and-post-training\u002Freferences\u002Ftuna-data-and-training.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_tuna_ranking_data.py","SCRIPT","脚本",11953,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmops\u002Fsub-skills\u002Fdistillation-and-post-training\u002Fscripts\u002Fcheck_tuna_ranking_data.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fmodel_parallel_conversion_plan.py",10552,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmops\u002Fsub-skills\u002Fdistillation-and-post-training\u002Fscripts\u002Fmodel_parallel_conversion_plan.py",[75,83,90,97,104,111],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]