[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791QEMKYB99GMB2F7MBX142":3,"skill-same:01M791QEMKYB99GMB2F7MBX142":66},{"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},"01M791QEMKYB99GMB2F7MBX142","model-usage",null,"Initialize OpenFlamingo models, load checkpoints, prepare multimodal prompts, run forward\u002Fgenerate, and debug media caching constraints.","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\u002Fopen-flamingo\u002Fsub-skills\u002Fmodel-usage\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-usage\ndescription: \"Initialize OpenFlamingo models, load checkpoints, prepare\n  multimodal prompts, run forward\u002Fgenerate, and debug media caching\n  constraints.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# OpenFlamingo Model Usage\n\nUse this sub-skill when a task requires OpenFlamingo model construction, checkpoint loading, prompt\u002Fmedia preprocessing, generation, log-likelihood style `forward()` calls, media caching, or architecture debugging.\n\nDo not start full model downloads, benchmark datasets, training, or evaluation unless the caller explicitly provides the required local files, network permission, hardware budget, and time budget. The safe default is to validate inputs and prepare code that works with a caller-supplied local cache or checkpoint.\n\n## Route by task\n\n- **Need API signatures or object relationships:** read [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n- **Need an offline\u002Flocal-cache generation recipe:** read [references\u002Fgeneration-workflows.md](references\u002Fgeneration-workflows.md).\n- **Need to fix token, tensor, checkpoint, cache, decoder-layer, or import errors:** read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- **Need a deterministic preflight check without downloads:** run [`scripts\u002Fvalidate_generation_inputs.py`](scripts\u002Fvalidate_generation_inputs.py).\n\n## Critical invariants\n\n- Public imports are `from open_flamingo import create_model_and_transforms, Flamingo`.\n- The package\u002Fdistribution identity is `open_flamingo` 2.0.1.\n- `vision_x` for `Flamingo.forward()` and `Flamingo.generate()` is `B x T_img x F x C x H x W`; current OpenFlamingo supports **`F=1` only**.\n- Text prompts must use the exact special tokens `\u003Cimage>` and `\u003C|endofchunk|>`. Each image\u002Fmedia item should have a matching `\u003Cimage>` token in the prompt for the same example.\n- For generation, set `tokenizer.padding_side = \"left\"` before tokenization and pass `attention_mask`.\n- `generate(num_beams=N)` internally repeats `vision_x` along batch dimension when `N > 1`; do not pre-repeat the media batch for beam search.\n- `cache_media()` is for repeated `forward()`\u002Fclassification-style scoring, not for `generate()`. After cached calls, call `uncache_media()`.\n\n## Safe input validation\n\nFrom this sub-skill directory, validate a three-image captioning prompt without importing OpenFlamingo or downloading anything:\n\n```bash\npython scripts\u002Fvalidate_generation_inputs.py \\\n  --batch-size 1 \\\n  --num-media 3 \\\n  --num-frames 1 \\\n  --channels 3 \\\n  --height 224 \\\n  --width 224 \\\n  --prompt '\u003Cimage>An image of two cats.\u003C|endofchunk|>\u003Cimage>An image of a sink.\u003C|endofchunk|>\u003Cimage>An image of'\n```\n\nIf the script exits nonzero, correct the reported shape\u002Ftoken issue before attempting model execution.\n","# OpenFlamingo Model Usage\n\nUse this sub-skill when a task requires OpenFlamingo model construction, checkpoint loading, prompt\u002Fmedia preprocessing, generation, log-likelihood style `forward()` calls, media caching, or architecture debugging.\n\nDo not start full model downloads, benchmark datasets, training, or evaluation unless the caller explicitly provides the required local files, network permission, hardware budget, and time budget. The safe default is to validate inputs and prepare code that works with a caller-supplied local cache or checkpoint.\n\n## Route by task\n\n- **Need API signatures or object relationships:** read [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n- **Need an offline\u002Flocal-cache generation recipe:** read [references\u002Fgeneration-workflows.md](references\u002Fgeneration-workflows.md).\n- **Need to fix token, tensor, checkpoint, cache, decoder-layer, or import errors:** read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- **Need a deterministic preflight check without downloads:** run [`scripts\u002Fvalidate_generation_inputs.py`](scripts\u002Fvalidate_generation_inputs.py).\n\n## Critical invariants\n\n- Public imports are `from open_flamingo import create_model_and_transforms, Flamingo`.\n- The package\u002Fdistribution identity is `open_flamingo` 2.0.1.\n- `vision_x` for `Flamingo.forward()` and `Flamingo.generate()` is `B x T_img x F x C x H x W`; current OpenFlamingo supports **`F=1` only**.\n- Text prompts must use the exact special tokens `\u003Cimage>` and `\u003C|endofchunk|>`. Each image\u002Fmedia item should have a matching `\u003Cimage>` token in the prompt for the same example.\n- For generation, set `tokenizer.padding_side = \"left\"` before tokenization and pass `attention_mask`.\n- `generate(num_beams=N)` internally repeats `vision_x` along batch dimension when `N > 1`; do not pre-repeat the media batch for beam search.\n- `cache_media()` is for repeated `forward()`\u002Fclassification-style scoring, not for `generate()`. After cached calls, call `uncache_media()`.\n\n## Safe input validation\n\nFrom this sub-skill directory, validate a three-image captioning prompt without importing OpenFlamingo or downloading anything:\n\n```bash\npython scripts\u002Fvalidate_generation_inputs.py \\\n  --batch-size 1 \\\n  --num-media 3 \\\n  --num-frames 1 \\\n  --channels 3 \\\n  --height 224 \\\n  --width 224 \\\n  --prompt '\u003Cimage>An image of two cats.\u003C|endofchunk|>\u003Cimage>An image of a sink.\u003C|endofchunk|>\u003Cimage>An image of'\n```\n\nIf the script exits nonzero, correct the reported shape\u002Ftoken issue before attempting model execution.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fopen-flamingo\u002Fsub-skills\u002Fmodel-usage",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-usage",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-usage",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-usage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-flamingo\u002Fsub-skills\u002Fmodel-usage\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",8745,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-flamingo\u002Fsub-skills\u002Fmodel-usage\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fgeneration-workflows.md",9402,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-flamingo\u002Fsub-skills\u002Fmodel-usage\u002Freferences\u002Fgeneration-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",9488,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-flamingo\u002Fsub-skills\u002Fmodel-usage\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fvalidate_generation_inputs.py","SCRIPT","脚本",7577,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopen-flamingo\u002Fsub-skills\u002Fmodel-usage\u002Fscripts\u002Fvalidate_generation_inputs.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]