[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SW6DGBCT566PA6DVQK7W9":3,"skill-same:01M78SW6DGBCT566PA6DVQK7W9":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},"01M78SW6DGBCT566PA6DVQK7W9","attention-is-all-you-need-pytorch",null,"Use jadore801120 attention-is-all-you-need-pytorch for Transformer architecture inspection, preprocessing, training, and checkpoint translation workflows.","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\u002Fattention-is-all-you-need-pytorch\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: attention-is-all-you-need-pytorch\ndescription: \"Use jadore801120 attention-is-all-you-need-pytorch for Transformer\n  architecture inspection, preprocessing, training, and checkpoint translation\n  workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# attention-is-all-you-need-pytorch\n\nUse this repo skill when a task involves the PyTorch implementation of the\nTransformer paper in `jadore801120\u002Fattention-is-all-you-need-pytorch`: model\ninternals, German-English preprocessing, training commands, or checkpoint\ntranslation. The repository is script\u002Fsource based rather than a packaged Python\ndistribution, so future users normally work from a checkout that contains\n`transformer\u002F`, `preprocess.py`, `train.py`, and `translate.py`.\n\n## Quick Setup And Smoke Check\n\nUse a legacy-compatible Python environment with PyTorch, legacy torchtext APIs,\nspaCy, dill, tqdm, and NumPy. The source expects `torchtext.data.Field`; modern\ntorchtext releases that removed this API will not work unchanged.\n\nMinimal import check from a user's checkout:\n\n```bash\npython - \u003C\u003C'PY'\nfrom transformer.Models import Transformer\nfrom transformer.Translator import Translator\nprint(Transformer)\nprint(Translator)\nPY\n```\n\nRun the bundled environment checker when diagnosing an existing checkout:\n\n```bash\npython scripts\u002Fcheck_environment.py --repo-root \u002Fpath\u002Fto\u002Fattention-is-all-you-need-pytorch --device cpu\n```\n\n## Route Map\n\n- [model-architecture](sub-skills\u002Fmodel-architecture\u002FSKILL.md): instantiate or\n  debug `Transformer`, masks, positional encoding, attention layers,\n  feed-forward blocks, weight sharing, tensor shapes, and `ScheduledOptim`.\n- [data-preparation](sub-skills\u002Fdata-preparation\u002FSKILL.md): prepare or inspect\n  Multi30k\u002FspaCy and WMT+BPE data artifacts, pickle schemas, torchtext Fields,\n  vocabularies, and BPE helper behavior.\n- [training](sub-skills\u002Ftraining\u002FSKILL.md): build and troubleshoot `train.py`\n  commands, hyperparameters, scheduler\u002Floss behavior, logs, checkpoints,\n  TensorBoard, CPU\u002FCUDA selection, and safe training preflights.\n- [translation](sub-skills\u002Ftranslation\u002FSKILL.md): validate checkpoints and data\n  pickles for `translate.py`, run checkpoint translation, or use\n  `transformer.Translator` beam search programmatically.\n\n## Repo-Level References\n\n- Read [references\u002Fpackage-overview.md](references\u002Fpackage-overview.md) for the\n  source layout, dependency expectations, workflow map, and known caveats.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for\n  cross-cutting install\u002Fimport, torchtext, spaCy, CUDA, pickle, and stale README\n  issues.\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before\n  deciding whether this skill is current for a checkout or should be refreshed.\n\n## Decision Hints\n\n- If the user asks about tensor dimensions, masks, weight sharing, or custom\n  model construction, route to model-architecture before training or translation.\n- If the user asks why training cannot read a pickle, route to data-preparation\n  first, then training after the schema is identified.\n- If the user asks about a `.chkpt` file, route to translation for checkpoint\n  inspection unless they are asking how the checkpoint was produced.\n- If the prompt mentions BPE, keep the repository caveat visible: BPE is marked\n  not fully tested and `translate.py` leaves BPE decoding as TODO.\n- If a README command fails with an unrecognized `-log` flag, prefer the\n  inspected `train.py` parser over the README example for this commit.\n","# attention-is-all-you-need-pytorch\n\nUse this repo skill when a task involves the PyTorch implementation of the\nTransformer paper in `jadore801120\u002Fattention-is-all-you-need-pytorch`: model\ninternals, German-English preprocessing, training commands, or checkpoint\ntranslation. The repository is script\u002Fsource based rather than a packaged Python\ndistribution, so future users normally work from a checkout that contains\n`transformer\u002F`, `preprocess.py`, `train.py`, and `translate.py`.\n\n## Quick Setup And Smoke Check\n\nUse a legacy-compatible Python environment with PyTorch, legacy torchtext APIs,\nspaCy, dill, tqdm, and NumPy. The source expects `torchtext.data.Field`; modern\ntorchtext releases that removed this API will not work unchanged.\n\nMinimal import check from a user's checkout:\n\n```bash\npython - \u003C\u003C'PY'\nfrom transformer.Models import Transformer\nfrom transformer.Translator import Translator\nprint(Transformer)\nprint(Translator)\nPY\n```\n\nRun the bundled environment checker when diagnosing an existing checkout:\n\n```bash\npython scripts\u002Fcheck_environment.py --repo-root \u002Fpath\u002Fto\u002Fattention-is-all-you-need-pytorch --device cpu\n```\n\n## Route Map\n\n- [model-architecture](sub-skills\u002Fmodel-architecture\u002FSKILL.md): instantiate or\n  debug `Transformer`, masks, positional encoding, attention layers,\n  feed-forward blocks, weight sharing, tensor shapes, and `ScheduledOptim`.\n- [data-preparation](sub-skills\u002Fdata-preparation\u002FSKILL.md): prepare or inspect\n  Multi30k\u002FspaCy and WMT+BPE data artifacts, pickle schemas, torchtext Fields,\n  vocabularies, and BPE helper behavior.\n- [training](sub-skills\u002Ftraining\u002FSKILL.md): build and troubleshoot `train.py`\n  commands, hyperparameters, scheduler\u002Floss behavior, logs, checkpoints,\n  TensorBoard, CPU\u002FCUDA selection, and safe training preflights.\n- [translation](sub-skills\u002Ftranslation\u002FSKILL.md): validate checkpoints and data\n  pickles for `translate.py`, run checkpoint translation, or use\n  `transformer.Translator` beam search programmatically.\n\n## Repo-Level References\n\n- Read [references\u002Fpackage-overview.md](references\u002Fpackage-overview.md) for the\n  source layout, dependency expectations, workflow map, and known caveats.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for\n  cross-cutting install\u002Fimport, torchtext, spaCy, CUDA, pickle, and stale README\n  issues.\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before\n  deciding whether this skill is current for a checkout or should be refreshed.\n\n## Decision Hints\n\n- If the user asks about tensor dimensions, masks, weight sharing, or custom\n  model construction, route to model-architecture before training or translation.\n- If the user asks why training cannot read a pickle, route to data-preparation\n  first, then training after the schema is identified.\n- If the user asks about a `.chkpt` file, route to translation for checkpoint\n  inspection unless they are asking how the checkpoint was produced.\n- If the prompt mentions BPE, keep the repository caveat visible: BPE is marked\n  not fully tested and `translate.py` leaves BPE decoding as TODO.\n- If a README command fails with an unrecognized `-log` flag, prefer the\n  inspected `train.py` parser over the README example for this commit.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fattention-is-all-you-need-pytorch",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 attention-is-all-you-need-pytorch",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill attention-is-all-you-need-pytorch",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill attention-is-all-you-need-pytorch","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fattention-is-all-you-need-pytorch\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fpackage-overview.md","REFERENCE","参考文档",3118,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fattention-is-all-you-need-pytorch\u002Freferences\u002Fpackage-overview.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",1784,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fattention-is-all-you-need-pytorch\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",587,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fattention-is-all-you-need-pytorch\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",2019,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fattention-is-all-you-need-pytorch\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_environment.py","SCRIPT","脚本",3677,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fattention-is-all-you-need-pytorch\u002Fscripts\u002Fcheck_environment.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",[],[]]