[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KD50QBPD2M70H4AC610KPM":3,"skill-same:01M6KD50QBPD2M70H4AC610KPM":58},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":41,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6KD50QBPD2M70H4AC610KPM","nlp-project-setup",null,"Set up Python environment for NLP and preference optimization projects.","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\u002Fb1-one-shot-claude-haiku-4-5\u002Fnlp-paper-reproduction\u002Fnlp-project-setup\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29,30],"nlp","setup","project setup","project","nlp project setup","python","Optimization","SET","projects","environment","up","Preference Optimization","for","2026-11-10 10:12:30",false,"---\nname: nlp-project-setup\ndescription: Set up Python environment for NLP and preference optimization projects.\n---\n\n# NLP Project Environment Setup\n\n## Environment Requirements for SimPO\n\n### Core Dependencies\n- **PyTorch**: Deep learning framework (torch, torchvision, torchaudio)\n- **Transformers**: Hugging Face library for LLMs\n- **NumPy**: Numerical computing\n- **SciPy**: Scientific computing utilities\n- **tqdm**: Progress bars for training loops\n\n### Optional but Recommended\n- **wandb**: Experiment tracking\n- **accelerate**: Distributed training\n- **bitsandbytes**: 8-bit optimization\n- **Flash-Attn**: Efficient attention\n\n## Installation Steps\n\n### 1. Check Python Version\n```bash\npython --version  # Should be 3.8+\npython -VV        # Detailed version info\n```\n\n### 2. Create Virtual Environment (Optional)\n```bash\npython -m venv venv\nsource venv\u002Fbin\u002Factivate  # On Windows: venv\\Scripts\\activate\n```\n\n### 3. Install Core Dependencies\n```bash\n# PyTorch (CUDA 12.1 example)\npip install torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu121\n\n# Transformers\npip install transformers\n\n# Other essentials\npip install numpy scipy tqdm\n```\n\n### 4. Verify Installation\n```bash\npython -c \"import torch; print(torch.__version__)\"\npython -c \"import transformers; print(transformers.__version__)\"\n```\n\n## Dependency Version Considerations\n\n### For SimPO Specifically\n- **transformers** >= 4.30.0 (for AutoTokenizer, model loading)\n- **torch** >= 1.13.0 (for modern PyTorch features)\n- **numpy** (for .npz file saving)\n\n### Compatibility Notes\n- Different CUDA versions may require different torch builds\n- GPU memory requirements: typically 10-20GB for 7B models\n- CPU-only mode works but is much slower\n\n## Requirements File\nCreate `requirements.txt`:\n```\ntorch>=1.13.0\ntransformers>=4.30.0\nnumpy\nscipy\ntqdm\naccelerate>=0.20.0\n```\n\nThen install:\n```bash\npip install -r requirements.txt\n```\n\n## Logging Installed Packages\n```bash\n# Save package list\npython -m pip freeze > \u002Froot\u002Fpython_info.txt\n\n# Or capture with version info\npython -VV >> \u002Froot\u002Fpython_info.txt\npython -m pip freeze >> \u002Froot\u002Fpython_info.txt\n```\n\n## Troubleshooting\n\n### CUDA\u002FGPU Issues\n```bash\n# Check if CUDA available\npython -c \"import torch; print(torch.cuda.is_available())\"\n\n# Find CUDA version\nnvidia-smi  # Shows CUDA version\n\n# Match PyTorch to CUDA version\n# Visit: https:\u002F\u002Fpytorch.org\u002Fget-started\u002Flocally\u002F\n```\n\n### Missing Dependencies\n```bash\n# Install specific package\npip install \u003Cpackage_name>\n\n# Or reinstall all from requirements\npip install --force-reinstall -r requirements.txt\n```\n\n### Version Conflicts\n```bash\n# Show package version\npip show \u003Cpackage_name>\n\n# Check compatibility\npip check\n```\n","# NLP Project Environment Setup\n\n## Environment Requirements for SimPO\n\n### Core Dependencies\n- **PyTorch**: Deep learning framework (torch, torchvision, torchaudio)\n- **Transformers**: Hugging Face library for LLMs\n- **NumPy**: Numerical computing\n- **SciPy**: Scientific computing utilities\n- **tqdm**: Progress bars for training loops\n\n### Optional but Recommended\n- **wandb**: Experiment tracking\n- **accelerate**: Distributed training\n- **bitsandbytes**: 8-bit optimization\n- **Flash-Attn**: Efficient attention\n\n## Installation Steps\n\n### 1. Check Python Version\n```bash\npython --version  # Should be 3.8+\npython -VV        # Detailed version info\n```\n\n### 2. Create Virtual Environment (Optional)\n```bash\npython -m venv venv\nsource venv\u002Fbin\u002Factivate  # On Windows: venv\\Scripts\\activate\n```\n\n### 3. Install Core Dependencies\n```bash\n# PyTorch (CUDA 12.1 example)\npip install torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu121\n\n# Transformers\npip install transformers\n\n# Other essentials\npip install numpy scipy tqdm\n```\n\n### 4. Verify Installation\n```bash\npython -c \"import torch; print(torch.__version__)\"\npython -c \"import transformers; print(transformers.__version__)\"\n```\n\n## Dependency Version Considerations\n\n### For SimPO Specifically\n- **transformers** >= 4.30.0 (for AutoTokenizer, model loading)\n- **torch** >= 1.13.0 (for modern PyTorch features)\n- **numpy** (for .npz file saving)\n\n### Compatibility Notes\n- Different CUDA versions may require different torch builds\n- GPU memory requirements: typically 10-20GB for 7B models\n- CPU-only mode works but is much slower\n\n## Requirements File\nCreate `requirements.txt`:\n```\ntorch>=1.13.0\ntransformers>=4.30.0\nnumpy\nscipy\ntqdm\naccelerate>=0.20.0\n```\n\nThen install:\n```bash\npip install -r requirements.txt\n```\n\n## Logging Installed Packages\n```bash\n# Save package list\npython -m pip freeze > \u002Froot\u002Fpython_info.txt\n\n# Or capture with version info\npython -VV >> \u002Froot\u002Fpython_info.txt\npython -m pip freeze >> \u002Froot\u002Fpython_info.txt\n```\n\n## Troubleshooting\n\n### CUDA\u002FGPU Issues\n```bash\n# Check if CUDA available\npython -c \"import torch; print(torch.cuda.is_available())\"\n\n# Find CUDA version\nnvidia-smi  # Shows CUDA version\n\n# Match PyTorch to CUDA version\n# Visit: https:\u002F\u002Fpytorch.org\u002Fget-started\u002Flocally\u002F\n```\n\n### Missing Dependencies\n```bash\n# Install specific package\npip install \u003Cpackage_name>\n\n# Or reinstall all from requirements\npip install --force-reinstall -r requirements.txt\n```\n\n### Version Conflicts\n```bash\n# Show package version\npip show \u003Cpackage_name>\n\n# Check compatibility\npip check\n```\n",{"name":5,"description":7},"main","726e1f79b96b0cb3d729d0e55a1c847e0b5353ae","skills\u002Fb1-one-shot-claude-haiku-4-5\u002Fnlp-paper-reproduction\u002Fnlp-project-setup",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":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add cxcscmu\u002FSkillLearnBench --skill nlp-project-setup",{"tool":50,"command":51},"bunx","bunx skills add cxcscmu\u002FSkillLearnBench --skill nlp-project-setup",{"tool":53,"command":54},"pnpm","pnpm dlx skills add cxcscmu\u002FSkillLearnBench --skill nlp-project-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb1-one-shot-claude-haiku-4-5\u002Fnlp-paper-reproduction\u002Fnlp-project-setup\u002FSKILL.md",true,[],[59,77,101,118,138,149],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":70,"publishedAt":31},"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",[65],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[71,72,73,74,75,76],"object counter","object","vision","computer","Computer Vision","image",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":86,"publishedAt":31},"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",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000023","Skill与智能体开发",[87,88,89,90,91,92,93,94,95,30,96,97,98,99,100],"workflow","planning","planning workflow","travel","travel planning","travel planning workflow","structured","performing","plan","user","it","requirements","essential","itineraries",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":31},"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",[],[108,109,110,111,112,113,28,90,114,115,91,116,30,117,88],"search","tool","dataset","bundled dataset search tool","restaurants","Tools","look","flights","you","database",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":31},"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",[],[125,126,127,30,128,129,130,131,132,133,134,135,116,136,137],"glm output","output","glm","tasks","metrics","json","basics","guidance","matching","verifier","processing","root","calibration",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":145,"publishedAt":31},"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",[144],{"categoryNo":84,"categoryName":85,"taxonomyType":68,"taxonomyTypeDesc":69},[146,137,127,126,132,131,128,19,147,30,148],"glm calibration","companion","metric",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":31},"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",[],[156,127,131,157,146,137,30,126,158,159,160,161,162,163,128],"glm basics","inspect","relevant","files","good","use","how","Evaluation"]