[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XVDSP8JB3HBJGMW3WR3P6":3,"skill-same:01M78XVDSP8JB3HBJGMW3WR3P6":67},{"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},"01M78XVDSP8JB3HBJGMW3WR3P6","modeling-and-evaluation",null,"Use for H2O LLM Studio model wrappers, losses, metrics, evaluation outputs, inference routing, plots, and AI-judge metric behavior.","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\u002Fh2o-llmstudio\u002Fsub-skills\u002Fmodeling-and-evaluation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: modeling-and-evaluation\ndescription: \"Use for H2O LLM Studio model wrappers, losses, metrics, evaluation\n  outputs, inference routing, plots, and AI-judge metric behavior.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# H2O LLM Studio modeling and evaluation\n\nUse this sub-skill when the task is about how H2O LLM Studio maps a problem type to model wrappers, losses, metrics, inference behavior, generated prediction outputs, validation plots, or AI-judge metrics.\n\nDo **not** use this sub-skill for:\n\n- creating or repairing experiment YAML\u002Fdata schemas: use `configuration-and-data`;\n- launching, scheduling, or debugging training runs: use `training-and-experiments`;\n- interactive chat, model-card export, or Hugging Face publishing: use `export-and-prompt`.\n\n## Operating workflow\n\n1. Identify the `problem_type` first. Valid modeling\u002Fevaluation problem types are:\n   `text_causal_language_modeling`, `text_sequence_to_sequence_modeling`,\n   `text_dpo_modeling`, `text_causal_classification_modeling`, and\n   `text_causal_regression_modeling`.\n2. Load [references\u002Fmodel-and-metric-reference.md](references\u002Fmodel-and-metric-reference.md) for class mappings, forward\u002Fgenerate contracts, losses, metric direction, and expected result keys.\n3. Load [references\u002Fevaluation-workflows.md](references\u002Fevaluation-workflows.md) for `run_inference`, `run_eval`, prediction files, plot files, generation-vs-forward routing, and GPT\u002FMT-Bench judge behavior.\n4. For unsupported metrics, NaNs, empty outputs, OpenAI\u002FAzure endpoint issues, missing `prompts\u002F`, or classification\u002Fregression shape errors, load [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n5. Use [scripts\u002Finspect_problem_type.py](scripts\u002Finspect_problem_type.py) for a safe local inspection that lists the configured model\u002Floss\u002Fmetric\u002Fplot classes without instantiating or downloading a model.\n\n## Quick commands\n\n```bash\npython scripts\u002Finspect_problem_type.py --problem-type text_causal_classification_modeling --list-metrics\npython scripts\u002Finspect_problem_type.py --problem-type all --json\npython scripts\u002Finspect_problem_type.py --problem-type text_dpo_modeling --verify-imports\n```\n\nThe inspection script is safe by default: it prints static and import-level metadata only. It does not start training, call an AI judge, load Hugging Face weights, or create model instances.\n\n## Decision rules\n\n- For generative validation metrics other than `Perplexity`, causal LM, sequence-to-sequence, and DPO use generation; `Perplexity` uses a forward pass.\n- Classification and regression are non-generation tasks. They always use a forward pass and postprocess logits or regression head outputs into predictions before metrics are computed.\n- `GPT` metrics call an OpenAI-compatible Chat Completions endpoint and can incur network cost. Require endpoint, credential, and budget confirmation before running; use static reasoning or mocked tests when possible.\n- Validation artifacts are written by the training\u002Fevaluation workflow, not by the model classes themselves. Expect raw prediction pickle, prediction CSV, and parquet plot data when evaluation reaches rank 0 successfully.\n","# H2O LLM Studio modeling and evaluation\n\nUse this sub-skill when the task is about how H2O LLM Studio maps a problem type to model wrappers, losses, metrics, inference behavior, generated prediction outputs, validation plots, or AI-judge metrics.\n\nDo **not** use this sub-skill for:\n\n- creating or repairing experiment YAML\u002Fdata schemas: use `configuration-and-data`;\n- launching, scheduling, or debugging training runs: use `training-and-experiments`;\n- interactive chat, model-card export, or Hugging Face publishing: use `export-and-prompt`.\n\n## Operating workflow\n\n1. Identify the `problem_type` first. Valid modeling\u002Fevaluation problem types are:\n   `text_causal_language_modeling`, `text_sequence_to_sequence_modeling`,\n   `text_dpo_modeling`, `text_causal_classification_modeling`, and\n   `text_causal_regression_modeling`.\n2. Load [references\u002Fmodel-and-metric-reference.md](references\u002Fmodel-and-metric-reference.md) for class mappings, forward\u002Fgenerate contracts, losses, metric direction, and expected result keys.\n3. Load [references\u002Fevaluation-workflows.md](references\u002Fevaluation-workflows.md) for `run_inference`, `run_eval`, prediction files, plot files, generation-vs-forward routing, and GPT\u002FMT-Bench judge behavior.\n4. For unsupported metrics, NaNs, empty outputs, OpenAI\u002FAzure endpoint issues, missing `prompts\u002F`, or classification\u002Fregression shape errors, load [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n5. Use [scripts\u002Finspect_problem_type.py](scripts\u002Finspect_problem_type.py) for a safe local inspection that lists the configured model\u002Floss\u002Fmetric\u002Fplot classes without instantiating or downloading a model.\n\n## Quick commands\n\n```bash\npython scripts\u002Finspect_problem_type.py --problem-type text_causal_classification_modeling --list-metrics\npython scripts\u002Finspect_problem_type.py --problem-type all --json\npython scripts\u002Finspect_problem_type.py --problem-type text_dpo_modeling --verify-imports\n```\n\nThe inspection script is safe by default: it prints static and import-level metadata only. It does not start training, call an AI judge, load Hugging Face weights, or create model instances.\n\n## Decision rules\n\n- For generative validation metrics other than `Perplexity`, causal LM, sequence-to-sequence, and DPO use generation; `Perplexity` uses a forward pass.\n- Classification and regression are non-generation tasks. They always use a forward pass and postprocess logits or regression head outputs into predictions before metrics are computed.\n- `GPT` metrics call an OpenAI-compatible Chat Completions endpoint and can incur network cost. Require endpoint, credential, and budget confirmation before running; use static reasoning or mocked tests when possible.\n- Validation artifacts are written by the training\u002Fevaluation workflow, not by the model classes themselves. Expect raw prediction pickle, prediction CSV, and parquet plot data when evaluation reaches rank 0 successfully.\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\u002Fh2o-llmstudio\u002Fsub-skills\u002Fmodeling-and-evaluation",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 modeling-and-evaluation",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill modeling-and-evaluation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill modeling-and-evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh2o-llmstudio\u002Fsub-skills\u002Fmodeling-and-evaluation\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fevaluation-workflows.md","REFERENCE","参考文档",8438,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh2o-llmstudio\u002Fsub-skills\u002Fmodeling-and-evaluation\u002Freferences\u002Fevaluation-workflows.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmodel-and-metric-reference.md",9983,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh2o-llmstudio\u002Fsub-skills\u002Fmodeling-and-evaluation\u002Freferences\u002Fmodel-and-metric-reference.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",7928,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh2o-llmstudio\u002Fsub-skills\u002Fmodeling-and-evaluation\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Finspect_problem_type.py","SCRIPT","脚本",14076,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fh2o-llmstudio\u002Fsub-skills\u002Fmodeling-and-evaluation\u002Fscripts\u002Finspect_problem_type.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]