[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795G71CBRDPTP01R0RW9M6N":3,"skill-same:01M795G71CBRDPTP01R0RW9M6N":70},{"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},"01M795G71CBRDPTP01R0RW9M6N","training-and-configs",null,"Author, inspect, adapt, and troubleshoot config-driven training and model construction for diffusion and autoencoding workflows in generative-models.","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\u002Fstability-ai-generative-models\u002Fsub-skills\u002Ftraining-and-configs\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: training-and-configs\ndescription: \"Author, inspect, adapt, and troubleshoot config-driven training\n  and model construction for diffusion and autoencoding workflows in\n  generative-models.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Training and Configs\n\nUse this sub-skill when a task involves `main.py --base`, OmegaConf dotlist overrides, `instantiate_from_config`, `DiffusionEngine` training configs, `AutoencodingEngine`, `GeneralConditioner`, toy MNIST configs, `USER` placeholders, resume behavior, or Lightning callbacks\u002Flog directories.\n\nDo not use this sub-skill for inference execution, checkpoint sampling, UI demos, or watermarking. Route SDXL\u002FAPI inference tasks to `..\u002Finference-api\u002FSKILL.md`, video sampling scripts to `..\u002Fvideo-sampling\u002FSKILL.md`, and demos or watermarking to `..\u002Fdemos-and-watermarking\u002FSKILL.md`.\n\n## What This Covers\n\n- Build and inspect `model`, `data`, and `lightning` YAML sections for config-driven training.\n- Trace nested `target`\u002F`params` objects that will be consumed by `instantiate_from_config`.\n- Adapt diffusion configs around `DiffusionEngine`, denoisers, samplers, losses, conditioners, and first-stage autoencoders.\n- Adapt autoencoding configs around `AutoencodingEngine` and legacy `AutoencoderKL` wrappers.\n- Reason about `main.py` merge order, CLI overrides, trainer defaults, logging, callbacks, and resume semantics.\n- Validate configs statically without starting training, downloading checkpoints, or probing GPUs.\n\n## Fast Static Check\n\nUse the bundled helper for safe inspection before any training command:\n\n```bash\npython sub-skills\u002Ftraining-and-configs\u002Fscripts\u002Finspect_training_config.py \\\n  --config path\u002Fto\u002Fbase.yaml \\\n  --dotlist lightning.trainer.devices=0 model.params.sampler_config.params.num_steps=10\n```\n\nAdd `--json` when another tool needs structured output. The helper parses and merges config files, reports top-level sections, target paths, placeholders, likely missing `target` keys, data assumptions, resume\u002Fname conflicts, and a command template. It never imports training modules, instantiates models, downloads datasets, loads checkpoints, or calls the trainer.\n\n## Required Mental Model\n\n`main.py` treats YAML as the source of truth. It loads every `--base` config from left to right, builds an OmegaConf dotlist from unknown CLI tokens, merges the dotlist last, pops `lightning` out of the project config, and then instantiates `config.model` and `config.data` by calling `instantiate_from_config` on each object.\n\nEvery object meant for `instantiate_from_config` needs:\n\n```yaml\ntarget: dotted.import.Path\nparams:\n  key: value\n```\n\n`target` resolves to a Python object and `params` are passed as keyword arguments. Missing `target` usually fails with `KeyError: Expected key `target` to instantiate.` Import typos fail later when the module\u002Fclass path cannot be imported.\n\n## Reference Map\n\n- `references\u002Fconfiguration.md` explains schema patterns, merge rules, target paths, placeholders, and safe overrides.\n- `references\u002Fapi-reference.md` records config-facing signatures and important target classes verified against `sgm` version `0.1.0`.\n- `references\u002Fworkflows.md` gives safe authoring, adaptation, resume, and validation workflows.\n- `references\u002Ftroubleshooting.md` maps common symptoms to recoveries.\n- `scripts\u002Finspect_training_config.py` provides executable static validation help.\n\n## Safety Rules\n\n- Prefer static inspection over `main.py` for validation; even `--train false --no-test true` can still instantiate model\u002Fdata objects and call data preparation.\n- Do not recommend long training, checkpoint downloads, webdataset reads, or MNIST\u002FCIFAR downloads as verification.\n- Treat `CKPT_PATH`, `DATA_PATH`, `USER` comments, and dataset shard URLs as placeholders until a human supplies local values.\n- Keep `--name` and `--resume` mutually exclusive; use `--resume_from_checkpoint` with `--name` only when intentionally creating a new log folder from a checkpoint.\n- Assume GPU defaults unless `lightning.trainer.accelerator` and `lightning.trainer.devices` are explicitly reviewed.\n","# Training and Configs\n\nUse this sub-skill when a task involves `main.py --base`, OmegaConf dotlist overrides, `instantiate_from_config`, `DiffusionEngine` training configs, `AutoencodingEngine`, `GeneralConditioner`, toy MNIST configs, `USER` placeholders, resume behavior, or Lightning callbacks\u002Flog directories.\n\nDo not use this sub-skill for inference execution, checkpoint sampling, UI demos, or watermarking. Route SDXL\u002FAPI inference tasks to `..\u002Finference-api\u002FSKILL.md`, video sampling scripts to `..\u002Fvideo-sampling\u002FSKILL.md`, and demos or watermarking to `..\u002Fdemos-and-watermarking\u002FSKILL.md`.\n\n## What This Covers\n\n- Build and inspect `model`, `data`, and `lightning` YAML sections for config-driven training.\n- Trace nested `target`\u002F`params` objects that will be consumed by `instantiate_from_config`.\n- Adapt diffusion configs around `DiffusionEngine`, denoisers, samplers, losses, conditioners, and first-stage autoencoders.\n- Adapt autoencoding configs around `AutoencodingEngine` and legacy `AutoencoderKL` wrappers.\n- Reason about `main.py` merge order, CLI overrides, trainer defaults, logging, callbacks, and resume semantics.\n- Validate configs statically without starting training, downloading checkpoints, or probing GPUs.\n\n## Fast Static Check\n\nUse the bundled helper for safe inspection before any training command:\n\n```bash\npython sub-skills\u002Ftraining-and-configs\u002Fscripts\u002Finspect_training_config.py \\\n  --config path\u002Fto\u002Fbase.yaml \\\n  --dotlist lightning.trainer.devices=0 model.params.sampler_config.params.num_steps=10\n```\n\nAdd `--json` when another tool needs structured output. The helper parses and merges config files, reports top-level sections, target paths, placeholders, likely missing `target` keys, data assumptions, resume\u002Fname conflicts, and a command template. It never imports training modules, instantiates models, downloads datasets, loads checkpoints, or calls the trainer.\n\n## Required Mental Model\n\n`main.py` treats YAML as the source of truth. It loads every `--base` config from left to right, builds an OmegaConf dotlist from unknown CLI tokens, merges the dotlist last, pops `lightning` out of the project config, and then instantiates `config.model` and `config.data` by calling `instantiate_from_config` on each object.\n\nEvery object meant for `instantiate_from_config` needs:\n\n```yaml\ntarget: dotted.import.Path\nparams:\n  key: value\n```\n\n`target` resolves to a Python object and `params` are passed as keyword arguments. Missing `target` usually fails with `KeyError: Expected key `target` to instantiate.` Import typos fail later when the module\u002Fclass path cannot be imported.\n\n## Reference Map\n\n- `references\u002Fconfiguration.md` explains schema patterns, merge rules, target paths, placeholders, and safe overrides.\n- `references\u002Fapi-reference.md` records config-facing signatures and important target classes verified against `sgm` version `0.1.0`.\n- `references\u002Fworkflows.md` gives safe authoring, adaptation, resume, and validation workflows.\n- `references\u002Ftroubleshooting.md` maps common symptoms to recoveries.\n- `scripts\u002Finspect_training_config.py` provides executable static validation help.\n\n## Safety Rules\n\n- Prefer static inspection over `main.py` for validation; even `--train false --no-test true` can still instantiate model\u002Fdata objects and call data preparation.\n- Do not recommend long training, checkpoint downloads, webdataset reads, or MNIST\u002FCIFAR downloads as verification.\n- Treat `CKPT_PATH`, `DATA_PATH`, `USER` comments, and dataset shard URLs as placeholders until a human supplies local values.\n- Keep `--name` and `--resume` mutually exclusive; use `--resume_from_checkpoint` with `--name` only when intentionally creating a new log folder from a checkpoint.\n- Assume GPU defaults unless `lightning.trainer.accelerator` and `lightning.trainer.devices` are explicitly reviewed.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fstability-ai-generative-models\u002Fsub-skills\u002Ftraining-and-configs",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 training-and-configs",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill training-and-configs",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill training-and-configs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstability-ai-generative-models\u002Fsub-skills\u002Ftraining-and-configs\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",10411,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstability-ai-generative-models\u002Fsub-skills\u002Ftraining-and-configs\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fconfiguration.md",10235,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstability-ai-generative-models\u002Fsub-skills\u002Ftraining-and-configs\u002Freferences\u002Fconfiguration.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",9946,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstability-ai-generative-models\u002Fsub-skills\u002Ftraining-and-configs\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fworkflows.md",9324,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstability-ai-generative-models\u002Fsub-skills\u002Ftraining-and-configs\u002Freferences\u002Fworkflows.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Finspect_training_config.py","SCRIPT","脚本",21074,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstability-ai-generative-models\u002Fsub-skills\u002Ftraining-and-configs\u002Fscripts\u002Finspect_training_config.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"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.","Apache-2.0","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":75,"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":75,"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":75,"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":75,"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":75,"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",[],[]]