[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KFSRRWYV51C6S8Y9JZX481":3,"skill-same:01M6KFSRRWYV51C6S8Y9JZX481":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":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6KFSRRWYV51C6S8Y9JZX481","run2_nlp-paper-reproduction",null,"Complete setup guide for reproducing NLP paper results with HuggingFace TRL\u002Ftransformers on Python 3.12 - use when setting up environments for preference optimization experiments.","cxcscmu\u002FSkillLearnBench","cxcscmu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F142838272?v=4","01M6KCQDFQWPDSN0MKZY96MSQP","01M6KCQDM7G70TKJ28NTSQC0RZ",93,"MIT","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb2-self-feedback-claude-sonnet-4-6\u002Fnlp-paper-reproduction\u002Frun2_nlp-paper-reproduction\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"run2 nlp paper reproduction","paper","nlp","up","huggingface trl","for","environments","with","Preference Optimization","TRL","complete","use","guide","results","Transformers","HuggingFace","Optimization","setup","experiments","python","2026-11-10 10:12:30",false,"---\nname: run2_nlp-paper-reproduction\ndescription: Complete setup guide for reproducing NLP paper results with HuggingFace TRL\u002Ftransformers on Python 3.12 - use when setting up environments for preference optimization experiments.\n---\n\n# NLP Paper Reproduction Setup Guide\n\n## Environment Detection\n```bash\n# Check what Python is available\nwhich python3 && python3 -V\nwhich python && python -V 2>\u002Fdev\u002Fnull || echo \"no 'python' command\"\n```\n\n## Package Installation (Python 3.12, system Python)\n**Important**: Python 3.12 may require `--break-system-packages` flag for pip.\n\n```bash\n# Step 1: PyTorch (CPU version for testing, or CUDA for training)\npython3 -m pip install torch==2.2.2 --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcpu --break-system-packages\n\n# Step 2: HuggingFace ecosystem\npython3 -m pip install transformers==4.44.2 accelerate==0.29.2 datasets==2.18.0 peft==0.7.1 --break-system-packages\n\n# Step 3: TRL (Transformer Reinforcement Learning)\npython3 -m pip install trl==0.9.6 --break-system-packages\n\n# Step 4: Missing dependencies (TRL 0.9.6 requires 'rich')\npython3 -m pip install rich --break-system-packages\n```\n\n## Import Test\n```python\nfrom scripts.simpo_trainer import SimPOTrainer  # must run from project root\n```\n\n## Running Unit Tests\nUnit tests import `from scripts.simpo_trainer import ...`, so they need PYTHONPATH:\n```bash\n# Method 1: Set PYTHONPATH to project root\nPYTHONPATH=\u002Froot\u002FSimPO python3 \u002Froot\u002FSimPO\u002Funit_test\u002Funit_test_1.py\n\n# Method 2: Run from project root with module path\ncd \u002Froot\u002FSimPO && PYTHONPATH=. python3 unit_test\u002Funit_test_1.py\n\n# With pytest\npython3 -m pip install pytest --break-system-packages\nPYTHONPATH=\u002Froot\u002FSimPO python3 -m pytest unit_test\u002F -v\n```\n\n## Logging Environment for Reproducibility\n```bash\npython3 -VV > \u002Froot\u002Fpython_info.txt\npython3 -m pip freeze >> \u002Froot\u002Fpython_info.txt\n```\n\n## Common Issues & Fixes\n\n### `ModuleNotFoundError: No module named 'scripts'`\n- Root cause: Working directory not set to project root\n- Fix: `PYTHONPATH=\u002Froot\u002FSimPO python3 unit_test\u002Funit_test_1.py`\n\n### `ModuleNotFoundError: No module named 'rich'`\n- Root cause: TRL 0.9.6 requires `rich` which isn't auto-installed\n- Fix: `python3 -m pip install rich --break-system-packages`\n\n### `ERROR: This environment is externally managed`\n- Root cause: Ubuntu 24.04+ restricts system pip\n- Fix: Add `--break-system-packages` flag to pip commands\n\n### PDF Reading\n```bash\n# Install poppler for PDF text extraction\napt-get install -y poppler-utils\npdftotext \u002Fpath\u002Fto\u002Fpaper.pdf \u002Ftmp\u002Fpaper.txt\ncat \u002Ftmp\u002Fpaper.txt\n```\n\n## TRL 0.9.6 API Notes\n- `from trl.trainer import CPOTrainer` — base class sometimes used\n- `from trl.trainer.utils import DPODataCollatorWithPadding, disable_dropout_in_model, pad_to_length, peft_module_casting_to_bf16, trl_sanitze_kwargs_for_tagging`\n- Note: `trl_sanitze_kwargs_for_tagging` (typo: \"sanitze\" not \"sanitize\") is intentional in trl source\n","# NLP Paper Reproduction Setup Guide\n\n## Environment Detection\n```bash\n# Check what Python is available\nwhich python3 && python3 -V\nwhich python && python -V 2>\u002Fdev\u002Fnull || echo \"no 'python' command\"\n```\n\n## Package Installation (Python 3.12, system Python)\n**Important**: Python 3.12 may require `--break-system-packages` flag for pip.\n\n```bash\n# Step 1: PyTorch (CPU version for testing, or CUDA for training)\npython3 -m pip install torch==2.2.2 --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcpu --break-system-packages\n\n# Step 2: HuggingFace ecosystem\npython3 -m pip install transformers==4.44.2 accelerate==0.29.2 datasets==2.18.0 peft==0.7.1 --break-system-packages\n\n# Step 3: TRL (Transformer Reinforcement Learning)\npython3 -m pip install trl==0.9.6 --break-system-packages\n\n# Step 4: Missing dependencies (TRL 0.9.6 requires 'rich')\npython3 -m pip install rich --break-system-packages\n```\n\n## Import Test\n```python\nfrom scripts.simpo_trainer import SimPOTrainer  # must run from project root\n```\n\n## Running Unit Tests\nUnit tests import `from scripts.simpo_trainer import ...`, so they need PYTHONPATH:\n```bash\n# Method 1: Set PYTHONPATH to project root\nPYTHONPATH=\u002Froot\u002FSimPO python3 \u002Froot\u002FSimPO\u002Funit_test\u002Funit_test_1.py\n\n# Method 2: Run from project root with module path\ncd \u002Froot\u002FSimPO && PYTHONPATH=. python3 unit_test\u002Funit_test_1.py\n\n# With pytest\npython3 -m pip install pytest --break-system-packages\nPYTHONPATH=\u002Froot\u002FSimPO python3 -m pytest unit_test\u002F -v\n```\n\n## Logging Environment for Reproducibility\n```bash\npython3 -VV > \u002Froot\u002Fpython_info.txt\npython3 -m pip freeze >> \u002Froot\u002Fpython_info.txt\n```\n\n## Common Issues & Fixes\n\n### `ModuleNotFoundError: No module named 'scripts'`\n- Root cause: Working directory not set to project root\n- Fix: `PYTHONPATH=\u002Froot\u002FSimPO python3 unit_test\u002Funit_test_1.py`\n\n### `ModuleNotFoundError: No module named 'rich'`\n- Root cause: TRL 0.9.6 requires `rich` which isn't auto-installed\n- Fix: `python3 -m pip install rich --break-system-packages`\n\n### `ERROR: This environment is externally managed`\n- Root cause: Ubuntu 24.04+ restricts system pip\n- Fix: Add `--break-system-packages` flag to pip commands\n\n### PDF Reading\n```bash\n# Install poppler for PDF text extraction\napt-get install -y poppler-utils\npdftotext \u002Fpath\u002Fto\u002Fpaper.pdf \u002Ftmp\u002Fpaper.txt\ncat \u002Ftmp\u002Fpaper.txt\n```\n\n## TRL 0.9.6 API Notes\n- `from trl.trainer import CPOTrainer` — base class sometimes used\n- `from trl.trainer.utils import DPODataCollatorWithPadding, disable_dropout_in_model, pad_to_length, peft_module_casting_to_bf16, trl_sanitze_kwargs_for_tagging`\n- Note: `trl_sanitze_kwargs_for_tagging` (typo: \"sanitze\" not \"sanitize\") is intentional in trl source\n",{"name":5,"description":7},"main","726e1f79b96b0cb3d729d0e55a1c847e0b5353ae","skills\u002Fb2-self-feedback-claude-sonnet-4-6\u002Fnlp-paper-reproduction\u002Frun2_nlp-paper-reproduction",7,"https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench","https:\u002F\u002Fcxcscmu.github.io\u002FSkillLearnBench","https:\u002F\u002Fgithub.com\u002Fcxcscmu","2026-10-02 22:55:36",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add cxcscmu\u002FSkillLearnBench --skill run2_nlp-paper-reproduction",{"tool":62,"command":63},"bunx","bunx skills add cxcscmu\u002FSkillLearnBench --skill run2_nlp-paper-reproduction",{"tool":65,"command":66},"pnpm","pnpm dlx skills add cxcscmu\u002FSkillLearnBench --skill run2_nlp-paper-reproduction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb2-self-feedback-claude-sonnet-4-6\u002Fnlp-paper-reproduction\u002Frun2_nlp-paper-reproduction\u002FSKILL.md",true,[],[71,87,111,128,148,159],{"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":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":80,"publishedAt":43},"01M6KM5KH175P5ABP5JMX2SBDQ","object_counter","Count occurrences of an object in the image using computer vision algorithm.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Fvideo-object-counting\u002Fobject_counter\u002FSKILL.md",[77],{"categoryNo":78,"categoryName":79,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[81,82,83,84,85,86],"object counter","object","vision","computer","Computer Vision","image",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":96,"publishedAt":43},"01M6KM51TMVXG79MMPCS6Y8G86","travel-planning-workflow","Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Ftravel-planning-workflow\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[97,98,99,100,101,102,103,104,105,28,106,107,108,109,110],"workflow","planning","planning workflow","travel","travel planning","travel planning workflow","structured","performing","plan","user","it","requirements","essential","itineraries",{"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":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":43},"01M6KM4DY820XHS9YTSK5QP5HD","bundled-dataset-search-tool","invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Fbundled-dataset-search-tool\u002FSKILL.md",[],[118,119,120,121,122,123,26,100,124,125,101,126,28,127,98],"search","tool","dataset","bundled dataset search tool","restaurants","Tools","look","flights","you","database",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":43},"01M6KM465BB9PQ0B548HQSVAWZ","glm-output","Output-processing guidance for GLM tasks. Especially useful after glm-basics and glm-calibration when you need verifier-matching metrics from output.nc and a final \u002Froot\u002Fmetrics.json.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-output\u002FSKILL.md",[],[135,136,137,28,138,139,140,141,142,143,144,145,126,146,147],"glm output","output","glm","tasks","metrics","json","basics","guidance","matching","verifier","processing","root","calibration",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":43},"01M6KM40KY3QWDW5W97S39R2BC","glm-calibration","Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-calibration\u002FSKILL.md",[154],{"categoryNo":94,"categoryName":95,"taxonomyType":20,"taxonomyTypeDesc":21},[156,147,137,136,142,141,138,40,157,28,158],"glm calibration","companion","metric",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":43},"01M6KM3VHHVSGMGHJQB3PPT6YG","glm-basics","A good starting point for GLM calibration tasks. Use to inspect glm3.nml, confirm how GLM runs, and identify the relevant files before moving on to calibration and output evaluation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-basics\u002FSKILL.md",[],[166,137,141,167,156,147,28,136,168,169,170,34,171,172,138],"glm basics","inspect","relevant","files","good","how","Evaluation"]