[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792PD0CABZX5TNSSNP6VJEB":3,"skill-same:01M792PD0CABZX5TNSSNP6VJEB":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},"01M792PD0CABZX5TNSSNP6VJEB","model-internals",null,"Explain and verify the photo2cartoon generator, discriminator, normalization layers, face-ID feature path, tensor utilities, and checkpoint structure.","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\u002Fphoto2cartoon\u002Fsub-skills\u002Fmodel-internals\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-internals\ndescription: \"Explain and verify the photo2cartoon generator, discriminator,\n  normalization layers, face-ID feature path, tensor utilities, and checkpoint\n  structure.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Model Internals\n\nUse this sub-skill for the model core only: architecture, forward signatures, normalization layers, checkpoint contents, and safe synthetic verification.\n\n## Start here\n\n- [Architecture reference](references\u002Farchitecture-reference.md) for generator\u002Fdiscriminator tuples, hourglass topology, Soft-AdaLIN \u002F LIN behavior, CAM heatmaps, and verified smoke shapes.\n- [Training object reference](references\u002Ftraining-object-reference.md) for `UgatitSadalinHourglass`, losses, optimizer setup, checkpoint keys, and save\u002Fload behavior.\n- [Face ID loss reference](references\u002Fface-id-loss.md) for `FaceFeatures`, MobileFaceNet cropping, 112×112 embeddings, and cosine-distance loss.\n- [Image and tensor utilities](references\u002Fimage-and-tensor-utils.md) for normalization range, CAM rendering, and helper semantics.\n- [Troubleshooting](references\u002Ftroubleshooting.md) for shape mismatch, checkpoint key errors, deprecated `F.upsample`, device mismatch, and missing face-ID assets.\n- [Synthetic smoke](scripts\u002Fmodel_forward_smoke.py) for safe forward checks and optional checkpoint\u002Fface-ID validation.\n\n## Route elsewhere\n\n- Inference commands, asset download steps, and end-user cartoon generation workflows -> `..\u002Fportrait-inference\u002F`\n- Face detection, alignment, crop, and segmentation details -> `..\u002Fpreprocessing\u002F`\n- Dataset layout, preprocessing batches, CLI training, and long-running optimization -> `..\u002Fdata-and-training\u002F`\n\n## What this sub-skill covers\n\n- `ResnetGenerator`, `Discriminator`, `HourGlass`, `HourGlassBlock`, `ResnetBlock`, `ResnetSoftAdaLINBlock`, `SoftAdaLIN`, `adaLIN`, and `LIN`\n- Generator and discriminator return tuples: `(out, cam_logit, heatmap)`\n- CAM logits and heatmap interpretation\n- Tensor normalization range used by the repo\n- Face-ID embedding path through `MobileFaceNet(512)`\n- Training checkpoint contents and safe load checks\n- Safe synthetic verification only; no downloads, no training, no destructive writes\n\n## Practical commands\n\n```bash\npython scripts\u002Fmodel_forward_smoke.py --help\npython scripts\u002Fmodel_forward_smoke.py --repo-root \u002Fpath\u002Fto\u002Fphoto2cartoon\npython scripts\u002Fmodel_forward_smoke.py --repo-root \u002Fpath\u002Fto\u002Fphoto2cartoon --checkpoint \u002Fpath\u002Fto\u002Fcheckpoint.pt --face-model \u002Fpath\u002Fto\u002Fmodel_mobilefacenet.pth\n```\n","# Model Internals\n\nUse this sub-skill for the model core only: architecture, forward signatures, normalization layers, checkpoint contents, and safe synthetic verification.\n\n## Start here\n\n- [Architecture reference](references\u002Farchitecture-reference.md) for generator\u002Fdiscriminator tuples, hourglass topology, Soft-AdaLIN \u002F LIN behavior, CAM heatmaps, and verified smoke shapes.\n- [Training object reference](references\u002Ftraining-object-reference.md) for `UgatitSadalinHourglass`, losses, optimizer setup, checkpoint keys, and save\u002Fload behavior.\n- [Face ID loss reference](references\u002Fface-id-loss.md) for `FaceFeatures`, MobileFaceNet cropping, 112×112 embeddings, and cosine-distance loss.\n- [Image and tensor utilities](references\u002Fimage-and-tensor-utils.md) for normalization range, CAM rendering, and helper semantics.\n- [Troubleshooting](references\u002Ftroubleshooting.md) for shape mismatch, checkpoint key errors, deprecated `F.upsample`, device mismatch, and missing face-ID assets.\n- [Synthetic smoke](scripts\u002Fmodel_forward_smoke.py) for safe forward checks and optional checkpoint\u002Fface-ID validation.\n\n## Route elsewhere\n\n- Inference commands, asset download steps, and end-user cartoon generation workflows -> `..\u002Fportrait-inference\u002F`\n- Face detection, alignment, crop, and segmentation details -> `..\u002Fpreprocessing\u002F`\n- Dataset layout, preprocessing batches, CLI training, and long-running optimization -> `..\u002Fdata-and-training\u002F`\n\n## What this sub-skill covers\n\n- `ResnetGenerator`, `Discriminator`, `HourGlass`, `HourGlassBlock`, `ResnetBlock`, `ResnetSoftAdaLINBlock`, `SoftAdaLIN`, `adaLIN`, and `LIN`\n- Generator and discriminator return tuples: `(out, cam_logit, heatmap)`\n- CAM logits and heatmap interpretation\n- Tensor normalization range used by the repo\n- Face-ID embedding path through `MobileFaceNet(512)`\n- Training checkpoint contents and safe load checks\n- Safe synthetic verification only; no downloads, no training, no destructive writes\n\n## Practical commands\n\n```bash\npython scripts\u002Fmodel_forward_smoke.py --help\npython scripts\u002Fmodel_forward_smoke.py --repo-root \u002Fpath\u002Fto\u002Fphoto2cartoon\npython scripts\u002Fmodel_forward_smoke.py --repo-root \u002Fpath\u002Fto\u002Fphoto2cartoon --checkpoint \u002Fpath\u002Fto\u002Fcheckpoint.pt --face-model \u002Fpath\u002Fto\u002Fmodel_mobilefacenet.pth\n```\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fphoto2cartoon\u002Fsub-skills\u002Fmodel-internals",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 model-internals",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-internals",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-internals","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphoto2cartoon\u002Fsub-skills\u002Fmodel-internals\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Farchitecture-reference.md","REFERENCE","参考文档",4604,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphoto2cartoon\u002Fsub-skills\u002Fmodel-internals\u002Freferences\u002Farchitecture-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fface-id-loss.md",2008,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphoto2cartoon\u002Fsub-skills\u002Fmodel-internals\u002Freferences\u002Fface-id-loss.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fimage-and-tensor-utils.md",2602,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphoto2cartoon\u002Fsub-skills\u002Fmodel-internals\u002Freferences\u002Fimage-and-tensor-utils.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftraining-object-reference.md",3940,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphoto2cartoon\u002Fsub-skills\u002Fmodel-internals\u002Freferences\u002Ftraining-object-reference.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",2859,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphoto2cartoon\u002Fsub-skills\u002Fmodel-internals\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fmodel_forward_smoke.py","SCRIPT","脚本",16648,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphoto2cartoon\u002Fsub-skills\u002Fmodel-internals\u002Fscripts\u002Fmodel_forward_smoke.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",[],[]]