[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F65PP87QMTPDD9ZQA2NRES":3,"skill-same:01M7F65PP87QMTPDD9ZQA2NRES":92},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":14,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M7F65PP87QMTPDD9ZQA2NRES","axolotl",null,"Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).","chaorenex1\u002Fhermes-home-content","chaorenex1","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23194925?v=4","01M7F5NA1D1D02R2MEMYQN2NZT","chan chan","01M7F5NA20KTHMTY2015CYM1TZ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Faxolotl\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\r\nname: axolotl\r\ndescription: \"Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).\"\r\nversion: 1.0.0\r\nauthor: Orchestra Research\r\nlicense: MIT\r\ndependencies: [axolotl, torch, transformers, datasets, peft, accelerate, deepspeed]\r\nplatforms: [linux, macos]\r\nmetadata:\r\n  hermes:\r\n    tags: [Fine-Tuning, Axolotl, LLM, LoRA, QLoRA, DPO, KTO, ORPO, GRPO, YAML, HuggingFace, DeepSpeed, Multimodal]\r\n\r\n---\r\n\r\n# Axolotl Skill\r\n\r\n## What's inside\r\n\r\nExpert guidance for fine-tuning LLMs with Axolotl — YAML configs, 100+ models, LoRA\u002FQLoRA, DPO\u002FKTO\u002FORPO\u002FGRPO, multimodal support.\r\n\r\nComprehensive assistance with axolotl development, generated from official documentation.\r\n\r\n## When to Use This Skill\r\n\r\nThis skill should be triggered when:\r\n- Working with axolotl\r\n- Asking about axolotl features or APIs\r\n- Implementing axolotl solutions\r\n- Debugging axolotl code\r\n- Learning axolotl best practices\r\n\r\n## Quick Reference\r\n\r\n### Common Patterns\r\n\r\n**Pattern 1:** To validate that acceptable data transfer speeds exist for your training job, running NCCL Tests can help pinpoint bottlenecks, for example:\r\n\r\n```\r\n.\u002Fbuild\u002Fall_reduce_perf -b 8 -e 128M -f 2 -g 3\r\n```\r\n\r\n**Pattern 2:** Configure your model to use FSDP in the Axolotl yaml. For example:\r\n\r\n```\r\nfsdp_version: 2\r\nfsdp_config:\r\n  offload_params: true\r\n  state_dict_type: FULL_STATE_DICT\r\n  auto_wrap_policy: TRANSFORMER_BASED_WRAP\r\n  transformer_layer_cls_to_wrap: LlamaDecoderLayer\r\n  reshard_after_forward: true\r\n```\r\n\r\n**Pattern 3:** The context_parallel_size should be a divisor of the total number of GPUs. For example:\r\n\r\n```\r\ncontext_parallel_size\r\n```\r\n\r\n**Pattern 4:** For example: - With 8 GPUs and no sequence parallelism: 8 different batches processed per step - With 8 GPUs and context_parallel_size=4: Only 2 different batches processed per step (each split across 4 GPUs) - If your per-GPU micro_batch_size is 2, the global batch size decreases from 16 to 4\r\n\r\n```\r\ncontext_parallel_size=4\r\n```\r\n\r\n**Pattern 5:** Setting save_compressed: true in your configuration enables saving models in a compressed format, which: - Reduces disk space usage by approximately 40% - Maintains compatibility with vLLM for accelerated inference - Maintains compatibility with llmcompressor for further optimization (example: quantization)\r\n\r\n```\r\nsave_compressed: true\r\n```\r\n\r\n**Pattern 6:** Note It is not necessary to place your integration in the integrations folder. It can be in any location, so long as it’s installed in a package in your python env. See this repo for an example: https:\u002F\u002Fgithub.com\u002Faxolotl-ai-cloud\u002Fdiff-transformer\r\n\r\n```\r\nintegrations\r\n```\r\n\r\n**Pattern 7:** Handle both single-example and batched data. - single example: sample[‘input_ids’] is a list[int] - batched data: sample[‘input_ids’] is a list[list[int]]\r\n\r\n```\r\nutils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)\r\n```\r\n\r\n### Example Code Patterns\r\n\r\n**Example 1** (python):\r\n```python\r\ncli.cloud.modal_.ModalCloud(config, app=None)\r\n```\r\n\r\n**Example 2** (python):\r\n```python\r\ncli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)\r\n```\r\n\r\n**Example 3** (python):\r\n```python\r\ncore.trainers.base.AxolotlTrainer(\r\n    *_args,\r\n    bench_data_collator=None,\r\n    eval_data_collator=None,\r\n    dataset_tags=None,\r\n    **kwargs,\r\n)\r\n```\r\n\r\n**Example 4** (python):\r\n```python\r\ncore.trainers.base.AxolotlTrainer.log(logs, start_time=None)\r\n```\r\n\r\n**Example 5** (python):\r\n```python\r\nprompt_strategies.input_output.RawInputOutputPrompter()\r\n```\r\n\r\n## Reference Files\r\n\r\nThis skill includes comprehensive documentation in `references\u002F`:\r\n\r\n- **api.md** - Api documentation\r\n- **dataset-formats.md** - Dataset-Formats documentation\r\n- **other.md** - Other documentation\r\n\r\nUse `view` to read specific reference files when detailed information is needed.\r\n\r\n## Working with This Skill\r\n\r\n### For Beginners\r\nStart with the getting_started or tutorials reference files for foundational concepts.\r\n\r\n### For Specific Features\r\nUse the appropriate category reference file (api, guides, etc.) for detailed information.\r\n\r\n### For Code Examples\r\nThe quick reference section above contains common patterns extracted from the official docs.\r\n\r\n## Resources\r\n\r\n### references\u002F\r\nOrganized documentation extracted from official sources. These files contain:\r\n- Detailed explanations\r\n- Code examples with language annotations\r\n- Links to original documentation\r\n- Table of contents for quick navigation\r\n\r\n### scripts\u002F\r\nAdd helper scripts here for common automation tasks.\r\n\r\n### assets\u002F\r\nAdd templates, boilerplate, or example projects here.\r\n\r\n## Notes\r\n\r\n- This skill was automatically generated from official documentation\r\n- Reference files preserve the structure and examples from source docs\r\n- Code examples include language detection for better syntax highlighting\r\n- Quick reference patterns are extracted from common usage examples in the docs\r\n\r\n## Updating\r\n\r\nTo refresh this skill with updated documentation:\r\n1. Re-run the scraper with the same configuration\r\n2. The skill will be rebuilt with the latest information\r\n\r\n\r\n","# Axolotl Skill\r\n\r\n## What's inside\r\n\r\nExpert guidance for fine-tuning LLMs with Axolotl — YAML configs, 100+ models, LoRA\u002FQLoRA, DPO\u002FKTO\u002FORPO\u002FGRPO, multimodal support.\r\n\r\nComprehensive assistance with axolotl development, generated from official documentation.\r\n\r\n## When to Use This Skill\r\n\r\nThis skill should be triggered when:\r\n- Working with axolotl\r\n- Asking about axolotl features or APIs\r\n- Implementing axolotl solutions\r\n- Debugging axolotl code\r\n- Learning axolotl best practices\r\n\r\n## Quick Reference\r\n\r\n### Common Patterns\r\n\r\n**Pattern 1:** To validate that acceptable data transfer speeds exist for your training job, running NCCL Tests can help pinpoint bottlenecks, for example:\r\n\r\n```\r\n.\u002Fbuild\u002Fall_reduce_perf -b 8 -e 128M -f 2 -g 3\r\n```\r\n\r\n**Pattern 2:** Configure your model to use FSDP in the Axolotl yaml. For example:\r\n\r\n```\r\nfsdp_version: 2\r\nfsdp_config:\r\n  offload_params: true\r\n  state_dict_type: FULL_STATE_DICT\r\n  auto_wrap_policy: TRANSFORMER_BASED_WRAP\r\n  transformer_layer_cls_to_wrap: LlamaDecoderLayer\r\n  reshard_after_forward: true\r\n```\r\n\r\n**Pattern 3:** The context_parallel_size should be a divisor of the total number of GPUs. For example:\r\n\r\n```\r\ncontext_parallel_size\r\n```\r\n\r\n**Pattern 4:** For example: - With 8 GPUs and no sequence parallelism: 8 different batches processed per step - With 8 GPUs and context_parallel_size=4: Only 2 different batches processed per step (each split across 4 GPUs) - If your per-GPU micro_batch_size is 2, the global batch size decreases from 16 to 4\r\n\r\n```\r\ncontext_parallel_size=4\r\n```\r\n\r\n**Pattern 5:** Setting save_compressed: true in your configuration enables saving models in a compressed format, which: - Reduces disk space usage by approximately 40% - Maintains compatibility with vLLM for accelerated inference - Maintains compatibility with llmcompressor for further optimization (example: quantization)\r\n\r\n```\r\nsave_compressed: true\r\n```\r\n\r\n**Pattern 6:** Note It is not necessary to place your integration in the integrations folder. It can be in any location, so long as it’s installed in a package in your python env. See this repo for an example: https:\u002F\u002Fgithub.com\u002Faxolotl-ai-cloud\u002Fdiff-transformer\r\n\r\n```\r\nintegrations\r\n```\r\n\r\n**Pattern 7:** Handle both single-example and batched data. - single example: sample[‘input_ids’] is a list[int] - batched data: sample[‘input_ids’] is a list[list[int]]\r\n\r\n```\r\nutils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)\r\n```\r\n\r\n### Example Code Patterns\r\n\r\n**Example 1** (python):\r\n```python\r\ncli.cloud.modal_.ModalCloud(config, app=None)\r\n```\r\n\r\n**Example 2** (python):\r\n```python\r\ncli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)\r\n```\r\n\r\n**Example 3** (python):\r\n```python\r\ncore.trainers.base.AxolotlTrainer(\r\n    *_args,\r\n    bench_data_collator=None,\r\n    eval_data_collator=None,\r\n    dataset_tags=None,\r\n    **kwargs,\r\n)\r\n```\r\n\r\n**Example 4** (python):\r\n```python\r\ncore.trainers.base.AxolotlTrainer.log(logs, start_time=None)\r\n```\r\n\r\n**Example 5** (python):\r\n```python\r\nprompt_strategies.input_output.RawInputOutputPrompter()\r\n```\r\n\r\n## Reference Files\r\n\r\nThis skill includes comprehensive documentation in `references\u002F`:\r\n\r\n- **api.md** - Api documentation\r\n- **dataset-formats.md** - Dataset-Formats documentation\r\n- **other.md** - Other documentation\r\n\r\nUse `view` to read specific reference files when detailed information is needed.\r\n\r\n## Working with This Skill\r\n\r\n### For Beginners\r\nStart with the getting_started or tutorials reference files for foundational concepts.\r\n\r\n### For Specific Features\r\nUse the appropriate category reference file (api, guides, etc.) for detailed information.\r\n\r\n### For Code Examples\r\nThe quick reference section above contains common patterns extracted from the official docs.\r\n\r\n## Resources\r\n\r\n### references\u002F\r\nOrganized documentation extracted from official sources. These files contain:\r\n- Detailed explanations\r\n- Code examples with language annotations\r\n- Links to original documentation\r\n- Table of contents for quick navigation\r\n\r\n### scripts\u002F\r\nAdd helper scripts here for common automation tasks.\r\n\r\n### assets\u002F\r\nAdd templates, boilerplate, or example projects here.\r\n\r\n## Notes\r\n\r\n- This skill was automatically generated from official documentation\r\n- Reference files preserve the structure and examples from source docs\r\n- Code examples include language detection for better syntax highlighting\r\n- Quick reference patterns are extracted from common usage examples in the docs\r\n\r\n## Updating\r\n\r\nTo refresh this skill with updated documentation:\r\n1. Re-run the scraper with the same configuration\r\n2. The skill will be rebuilt with the latest information\r\n\r\n\r\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":42,"description":7,"dependencies":45},"Orchestra Research","1.0.0",{"hermes":27},{"tags":28},[29,30,31,32,33,34,35,36,37,38,39,40,41],"Fine-Tuning","Axolotl","LLM","LoRA","QLoRA","DPO","KTO","ORPO","GRPO","YAML","HuggingFace","DeepSpeed","Multimodal",[43,44],"linux","macos",[5,46,47,48,49,50,51],"torch","transformers","datasets","peft","accelerate","deepspeed","main","a3f3199bb87ec3c91248f68a39d88527e1847ae9","skills\u002Faxolotl","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content","https:\u002F\u002Fgithub.com\u002Fchaorenex1","https:\u002F\u002Fblog.aduib.com","A programmer whose only hobby in life is coding","2026-10-20 00:34:32",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add chaorenex1\u002Fhermes-home-content --skill axolotl",{"tool":66,"command":67},"bunx","bunx skills add chaorenex1\u002Fhermes-home-content --skill axolotl",{"tool":69,"command":70},"pnpm","pnpm dlx skills add chaorenex1\u002Fhermes-home-content --skill axolotl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Faxolotl\u002FSKILL.md",true,[74,80,84,88],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fapi.md","REFERENCE","参考文档",126692,"https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Faxolotl\u002Freferences\u002Fapi.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fdataset-formats.md",47072,"https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Faxolotl\u002Freferences\u002Fdataset-formats.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Findex.md",214,"https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Faxolotl\u002Freferences\u002Findex.md",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fother.md",143968,"https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Faxolotl\u002Freferences\u002Fother.md",[93,100,107,114,121,128],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7F8GF32YD5MBQW2TGSRH1YP","web-retrieval-resilience","Web tools fail or search rules break: repair or fall back.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fweb-retrieval-resilience\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7F8FP46QESQMCZ1KBT3TW3R","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7F8ER6VXHBNVRQBZS7X08SE","verification-loop","Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage, security grep, and diff review — then produce a PASS\u002FFAIL verification report. Use when verifying work after completing a feature or refactor, before creating a PR, or when quality gates must pass.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7F8E4BQJ38KVQVM3MT20PYV","unreal-world-builder","开放世界与环境专家——精通 UE5 World Partition、Landscape、程序化植被、HLOD 和大规模关卡流式加载，打造无缝开放世界体验","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-world-builder\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M7F8D747SQW2FTP7GBSX38BR","unreal-technical-artist","Unreal Engine 视觉管线专家——精通材质编辑器、Niagara 特效、程序化内容生成和 UE5 项目的美术到引擎管线","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-technical-artist\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":19},"01M7F8CKHYJVZVBTN0321J88T2","unreal-systems-engineer","性能与混合架构专家——精通 C++\u002FBlueprint 边界、Nanite 几何体、Lumen GI 和 Gameplay Ability System，面向 AAA 级 Unreal Engine 项目","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-systems-engineer\u002FSKILL.md",[],[]]