[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C3XH2FVRPAXCBXH6M6DZ8C":3,"skill-same:01M7C3XH2FVRPAXCBXH6M6DZ8C":89},{"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":51,"commitSha":52,"skillDirectory":53,"forksCount":13,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M7C3XH2FVRPAXCBXH6M6DZ8C","axolotl",null,"Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).","fengwhang\u002Fmercury","fengwhang","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F325040254?v=4","01M7C3K54Y41KVGPHEMKEP9X70","01M7C3K55NTZ4B36YP2JY1NMJ0",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fhermes\u002Foptional-skills\u002Fmlops\u002Ftraining\u002Faxolotl\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: axolotl\ndescription: \"Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).\"\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ndependencies: [axolotl, torch, transformers, datasets, peft, accelerate, deepspeed]\nplatforms: [linux, macos]\nmetadata:\n  mercury:\n    tags: [Fine-Tuning, Axolotl, LLM, LoRA, QLoRA, DPO, KTO, ORPO, GRPO, YAML, HuggingFace, DeepSpeed, Multimodal]\n\n---\n\n# Axolotl Skill\n\n## What's inside\n\nExpert guidance for fine-tuning LLMs with Axolotl — YAML configs, 100+ models, LoRA\u002FQLoRA, DPO\u002FKTO\u002FORPO\u002FGRPO, multimodal support.\n\nAssistance with axolotl development, generated from official documentation.\n\n## When to Use This Skill\n\nThis skill should be triggered when:\n- Working with axolotl\n- Asking about axolotl features or APIs\n- Implementing axolotl solutions\n- Debugging axolotl code\n- Learning axolotl best practices\n\n## Quick Reference\n\n### Common Patterns\n\n**Pattern 1:** To validate that acceptable data transfer speeds exist for your training job, running NCCL Tests can help pinpoint bottlenecks, for example:\n\n```\n.\u002Fbuild\u002Fall_reduce_perf -b 8 -e 128M -f 2 -g 3\n```\n\n**Pattern 2:** Configure your model to use FSDP in the Axolotl yaml. For example:\n\n```\nfsdp_version: 2\nfsdp_config:\n  offload_params: true\n  state_dict_type: FULL_STATE_DICT\n  auto_wrap_policy: TRANSFORMER_BASED_WRAP\n  transformer_layer_cls_to_wrap: LlamaDecoderLayer\n  reshard_after_forward: true\n```\n\n**Pattern 3:** The context_parallel_size should be a divisor of the total number of GPUs. For example:\n\n```\ncontext_parallel_size\n```\n\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\n\n```\ncontext_parallel_size=4\n```\n\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)\n\n```\nsave_compressed: true\n```\n\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\n\n```\nintegrations\n```\n\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]]\n\n```\nutils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)\n```\n\n### Example Code Patterns\n\n**Example 1** (python):\n```python\ncli.cloud.modal_.ModalCloud(config, app=None)\n```\n\n**Example 2** (python):\n```python\ncli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)\n```\n\n**Example 3** (python):\n```python\ncore.trainers.base.AxolotlTrainer(\n    *_args,\n    bench_data_collator=None,\n    eval_data_collator=None,\n    dataset_tags=None,\n    **kwargs,\n)\n```\n\n**Example 4** (python):\n```python\ncore.trainers.base.AxolotlTrainer.log(logs, start_time=None)\n```\n\n**Example 5** (python):\n```python\nprompt_strategies.input_output.RawInputOutputPrompter()\n```\n\n## Reference Files\n\nThis skill includes comprehensive documentation in `references\u002F`:\n\n- **api.md** - Api documentation\n- **dataset-formats.md** - Dataset-Formats documentation\n- **other.md** - Other documentation\n\nUse `view` to read specific reference files when detailed information is needed.\n\n## Working with This Skill\n\n### For Beginners\nStart with the getting_started or tutorials reference files for foundational concepts.\n\n### For Specific Features\nUse the appropriate category reference file (api, guides, etc.) for detailed information.\n\n### For Code Examples\nThe quick reference section above contains common patterns extracted from the official docs.\n\n## Resources\n\n### references\u002F\nOrganized documentation extracted from official sources. These files contain:\n- Detailed explanations\n- Code examples with language annotations\n- Links to original documentation\n- Table of contents for quick navigation\n\n### scripts\u002F\nAdd helper scripts here for common automation tasks.\n\n### assets\u002F\nAdd templates, boilerplate, or example projects here.\n\n## Notes\n\n- This skill was automatically generated from official documentation\n- Reference files preserve the structure and examples from source docs\n- Code examples include language detection for better syntax highlighting\n- Quick reference patterns are extracted from common usage examples in the docs\n\n## Updating\n\nTo refresh this skill with updated documentation:\n1. Re-run the scraper with the same configuration\n2. The skill will be rebuilt with the latest information\n\n\n","# Axolotl Skill\n\n## What's inside\n\nExpert guidance for fine-tuning LLMs with Axolotl — YAML configs, 100+ models, LoRA\u002FQLoRA, DPO\u002FKTO\u002FORPO\u002FGRPO, multimodal support.\n\nAssistance with axolotl development, generated from official documentation.\n\n## When to Use This Skill\n\nThis skill should be triggered when:\n- Working with axolotl\n- Asking about axolotl features or APIs\n- Implementing axolotl solutions\n- Debugging axolotl code\n- Learning axolotl best practices\n\n## Quick Reference\n\n### Common Patterns\n\n**Pattern 1:** To validate that acceptable data transfer speeds exist for your training job, running NCCL Tests can help pinpoint bottlenecks, for example:\n\n```\n.\u002Fbuild\u002Fall_reduce_perf -b 8 -e 128M -f 2 -g 3\n```\n\n**Pattern 2:** Configure your model to use FSDP in the Axolotl yaml. For example:\n\n```\nfsdp_version: 2\nfsdp_config:\n  offload_params: true\n  state_dict_type: FULL_STATE_DICT\n  auto_wrap_policy: TRANSFORMER_BASED_WRAP\n  transformer_layer_cls_to_wrap: LlamaDecoderLayer\n  reshard_after_forward: true\n```\n\n**Pattern 3:** The context_parallel_size should be a divisor of the total number of GPUs. For example:\n\n```\ncontext_parallel_size\n```\n\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\n\n```\ncontext_parallel_size=4\n```\n\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)\n\n```\nsave_compressed: true\n```\n\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\n\n```\nintegrations\n```\n\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]]\n\n```\nutils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)\n```\n\n### Example Code Patterns\n\n**Example 1** (python):\n```python\ncli.cloud.modal_.ModalCloud(config, app=None)\n```\n\n**Example 2** (python):\n```python\ncli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)\n```\n\n**Example 3** (python):\n```python\ncore.trainers.base.AxolotlTrainer(\n    *_args,\n    bench_data_collator=None,\n    eval_data_collator=None,\n    dataset_tags=None,\n    **kwargs,\n)\n```\n\n**Example 4** (python):\n```python\ncore.trainers.base.AxolotlTrainer.log(logs, start_time=None)\n```\n\n**Example 5** (python):\n```python\nprompt_strategies.input_output.RawInputOutputPrompter()\n```\n\n## Reference Files\n\nThis skill includes comprehensive documentation in `references\u002F`:\n\n- **api.md** - Api documentation\n- **dataset-formats.md** - Dataset-Formats documentation\n- **other.md** - Other documentation\n\nUse `view` to read specific reference files when detailed information is needed.\n\n## Working with This Skill\n\n### For Beginners\nStart with the getting_started or tutorials reference files for foundational concepts.\n\n### For Specific Features\nUse the appropriate category reference file (api, guides, etc.) for detailed information.\n\n### For Code Examples\nThe quick reference section above contains common patterns extracted from the official docs.\n\n## Resources\n\n### references\u002F\nOrganized documentation extracted from official sources. These files contain:\n- Detailed explanations\n- Code examples with language annotations\n- Links to original documentation\n- Table of contents for quick navigation\n\n### scripts\u002F\nAdd helper scripts here for common automation tasks.\n\n### assets\u002F\nAdd templates, boilerplate, or example projects here.\n\n## Notes\n\n- This skill was automatically generated from official documentation\n- Reference files preserve the structure and examples from source docs\n- Code examples include language detection for better syntax highlighting\n- Quick reference patterns are extracted from common usage examples in the docs\n\n## Updating\n\nTo refresh this skill with updated documentation:\n1. Re-run the scraper with the same configuration\n2. The skill will be rebuilt with the latest information\n\n\n",{"name":5,"author":23,"license":14,"version":24,"metadata":25,"platforms":41,"description":7,"dependencies":44},"Orchestra Research","1.0.0",{"mercury":26},{"tags":27},[28,29,30,31,32,33,34,35,36,37,38,39,40],"Fine-Tuning","Axolotl","LLM","LoRA","QLoRA","DPO","KTO","ORPO","GRPO","YAML","HuggingFace","DeepSpeed","Multimodal",[42,43],"linux","macos",[5,45,46,47,48,49,50],"torch","transformers","datasets","peft","accelerate","deepspeed","main","94a12cab2ce32e2020d179b5d579d0cbcbd0f206","hermes\u002Foptional-skills\u002Fmlops\u002Ftraining\u002Faxolotl","https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury","https:\u002F\u002Fgithub.com\u002Ffengwhang","2026-10-09 08:26:42",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add fengwhang\u002Fmercury --skill axolotl",{"tool":63,"command":64},"bunx","bunx skills add fengwhang\u002Fmercury --skill axolotl",{"tool":66,"command":67},"pnpm","pnpm dlx skills add fengwhang\u002Fmercury --skill axolotl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fhermes\u002Foptional-skills\u002Fmlops\u002Ftraining\u002Faxolotl\u002FSKILL.md",true,[71,77,81,85],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fapi.md","REFERENCE","参考文档",121144,"https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fhermes\u002Foptional-skills\u002Fmlops\u002Ftraining\u002Faxolotl\u002Freferences\u002Fapi.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fdataset-formats.md",46043,"https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fhermes\u002Foptional-skills\u002Fmlops\u002Ftraining\u002Faxolotl\u002Freferences\u002Fdataset-formats.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Findex.md",199,"https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fhermes\u002Foptional-skills\u002Fmlops\u002Ftraining\u002Faxolotl\u002Freferences\u002Findex.md",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fother.md",140405,"https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fhermes\u002Foptional-skills\u002Fmlops\u002Ftraining\u002Faxolotl\u002Freferences\u002Fother.md",[90,97,104,111,117,124],{"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":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M7C4BTY3ND38CN200ZCTH6NV","greet","A greeting skill for testing","https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fomp\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Fmarketplace\u002Ffixtures\u002Fvalid-marketplace\u002Fplugins\u002Fhello-plugin\u002Fskills\u002Fgreet\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":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M7C4BSNZTPW8JR5NGCQXGSEZ","valid-skill","A valid skill for testing purposes.","https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fomp\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fvalid-skill\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":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M7C4BRA7J8C06KSVW100F1W1","unknown-field","A skill with an unknown frontmatter field.","https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fomp\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Funknown-field\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":18},"01M7C4BNB04KQGCJ835JE8AR13","no-frontmatter","https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fomp\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fno-frontmatter\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":18},"01M7C4BM38TZFYT1AJ6SKHPZZ2","child-skill","A nested skill in a subdirectory.","https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fomp\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fnested\u002Fchild-skill\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":18},"01M7C4BJDN7RFFCM28CGX15Q97","different-name","A skill with a name that doesn't match the directory.","https:\u002F\u002Fgithub.com\u002Ffengwhang\u002Fmercury\u002Fblob\u002Fmain\u002Fomp\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fname-mismatch\u002FSKILL.md",[],[]]