[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-asset-fde5bef1":3,"seo:featured-workflow:fde5bef1-4ea3-11f1-9bc6-00163e2b0d79:zh":84,"workflow-related-asset-fde5bef1-fde5bef1-4ea3-11f1-9bc6-00163e2b0d79":85},{"id":4,"uuid":5,"slug":6,"title":7,"description":8,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":12,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":15,"tags":22,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":29,"asset_kind":30,"target_tools":31,"install_mode":35,"entrypoint":19,"risk_profile":36,"dependencies":38,"verification":44,"agent_metadata":47,"agent_fit":60,"trust":72,"provenance":81,"created_at":83,"updated_at":83},3572,"fde5bef1-4ea3-11f1-9bc6-00163e2b0d79","asset-fde5bef1","minGPT — Minimal PyTorch GPT Implementation for Learning","minGPT by Andrej Karpathy is a clean, readable re-implementation of GPT in about 300 lines of PyTorch, designed for educational use and as a starting point for GPT-based research experiments.","8a910e34-3180-11f1-9bc6-00163e2b0d79","Script Depot","https:\u002F\u002Ftokrepo.com\u002Fapple-touch-icon.png",0,"","en",[16],{"id":17,"step_order":18,"title":19,"description":13,"prompt_template":20,"variables":13,"depends_on":21,"expected_output":13},4132,1,"minGPT Overview","# minGPT — Minimal PyTorch GPT Implementation for Learning\n\n## Quick Use\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fkarpathy\u002FminGPT.git\ncd minGPT\npip install torch\npython demo.py\n```\n\n## Introduction\nminGPT is a minimal re-implementation of the GPT architecture in PyTorch by Andrej Karpathy. It strips away production complexity to expose the core transformer mechanics in clean, well-commented code, making it a go-to educational resource for understanding how GPT models work from the ground up.\n\n## What minGPT Does\n- Implements GPT-2 architecture in roughly 300 lines of PyTorch\n- Supports training from scratch on custom text datasets\n- Includes character-level and token-level language modeling demos\n- Provides a clean reference for the transformer decoder stack\n- Ships with example notebooks for sorting, math, and text generation\n\n## Architecture Overview\nminGPT implements a standard decoder-only transformer with causal self-attention, layer normalization, and a feedforward MLP block at each layer. The model class handles token and positional embeddings, the stack of transformer blocks, and the final language model head. Training logic is separated into a Trainer class that manages the optimization loop.\n\n## Self-Hosting & Configuration\n- Clone the repository and install PyTorch\n- Configure model size (number of layers, heads, embedding dim) via a simple config dict\n- Train on any text file with the included dataset utilities\n- Adjust learning rate, batch size, and context length as needed\n- Supports GPU training with standard PyTorch device placement\n\n## Key Features\n- Extremely readable codebase ideal for learning transformers\n- Faithful GPT-2 architecture with no unnecessary abstractions\n- Supports loading pre-trained GPT-2 weights from Hugging Face\n- Includes interactive Jupyter notebooks with training demos\n- Written by one of the original architects of modern deep learning education\n\n## Comparison with Similar Tools\n- **nanoGPT** — Karpathy's faster successor focused on training speed; minGPT prioritizes readability\n- **Hugging Face Transformers** — production library with hundreds of models; minGPT is a single-model educational tool\n- **GPT-2 (OpenAI)** — original TensorFlow implementation; minGPT is a clean PyTorch rewrite\n- **x-transformers** — modular transformer library; minGPT is intentionally minimal\n\n## FAQ\n**Q: Can minGPT train large models?**\nA: It can train small to medium GPT models. For large-scale training, nanoGPT or Hugging Face is more appropriate.\n\n**Q: Does it support fine-tuning pre-trained models?**\nA: Yes, it can load GPT-2 weights from Hugging Face and fine-tune on custom data.\n\n**Q: What Python version is required?**\nA: Python 3.7 or later with PyTorch 1.x or 2.x.\n\n**Q: Is this suitable for production use?**\nA: No, it is designed for education and experimentation. Use production frameworks for deployment.\n\n## Sources\n- https:\u002F\u002Fgithub.com\u002Fkarpathy\u002FminGPT","0",[23],{"id":24,"name":25,"slug":26,"icon":27},11,"Scripts","script","📜",false,"933734d7a21d50ca6920d8cc0b4d9f4c6f588114595204eb3d59bcff03e269ee","skill",[32,33,34],"claude_code","codex","gemini_cli","single",{"executes_code":28,"modifies_global_config":28,"requires_secrets":37,"uses_absolute_paths":28,"network_access":28},[],{"npm":39,"pip":40,"brew":42,"system":43},[],[41],"torch",[],[],{"commands":45,"expected_files":46},[],[19],{"asset_kind":30,"target_tools":48,"install_mode":35,"entrypoint":19,"risk_profile":49,"dependencies":51,"content_hash":29,"verification":56,"inferred":59},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":50,"uses_absolute_paths":28,"network_access":28},[],{"npm":52,"pip":53,"brew":54,"system":55},[],[41],[],[],{"commands":57,"expected_files":58},[],[19],true,{"target":33,"score":61,"status":62,"policy":63,"why":64,"asset_kind":30,"install_mode":35},98,"native","allow",[65,66,67,68,69,70,71],"target_tools includes codex","asset_kind skill","install_mode single","markdown-only","policy allow","safe markdown-only Codex install","trust established",{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":29,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":75,"review_status":76,"signals":77},"established","hash_only",[],"unreviewed",[78,79,80],"author has published assets","content hash available","no dangerous capability badges",{"owner_uuid":9,"owner_name":10,"source_url":82,"content_hash":29,"visibility":18,"created_at":83,"updated_at":83},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-fde5bef1","2026-05-13 16:16:07",null,[86,138,191,239],{"id":87,"uuid":88,"slug":89,"title":90,"description":91,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":92,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":93,"tags":94,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":96,"asset_kind":30,"target_tools":97,"install_mode":35,"entrypoint":98,"risk_profile":99,"dependencies":101,"verification":106,"agent_metadata":109,"agent_fit":121,"trust":123,"provenance":126,"created_at":128,"updated_at":129,"__relatedScore":130,"__relatedReasons":131,"__sharedTags":136},1946,"75b471b3-3e26-11f1-9bc6-00163e2b0d79","stable-baselines3-reliable-reinforcement-learning-75b471b3","Stable Baselines3 — Reliable Reinforcement Learning Implementations in PyTorch","Stable Baselines3 is a set of reliable, well-tested reinforcement learning algorithm implementations in PyTorch, designed as a plug-and-play toolkit for RL research and applications.",75,[],[95],{"id":24,"name":25,"slug":26,"icon":27},"c531fafb520762095b186ec52e0f95defa9911aad95cedf6511bdbdb77acc7a7",[32,33,34],"Stable Baselines3 RL",{"executes_code":28,"modifies_global_config":28,"requires_secrets":100,"uses_absolute_paths":28,"network_access":28},[],{"npm":102,"pip":103,"brew":104,"system":105},[],[],[],[],{"commands":107,"expected_files":108},[],[98],{"asset_kind":30,"target_tools":110,"install_mode":35,"entrypoint":98,"risk_profile":111,"dependencies":113,"content_hash":96,"verification":118},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":112,"uses_absolute_paths":28,"network_access":28},[],{"npm":114,"pip":115,"brew":116,"system":117},[],[],[],[],{"commands":119,"expected_files":120},[],[98],{"target":33,"score":61,"status":62,"policy":63,"why":122,"asset_kind":30,"install_mode":35},[65,66,67,68,69,70,71],{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":96,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":124,"review_status":76,"signals":125},[],[78,79,80],{"owner_uuid":9,"owner_name":10,"source_url":127,"content_hash":96,"visibility":18,"created_at":128,"updated_at":129},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fstable-baselines3-reliable-reinforcement-learning-75b471b3","2026-04-22 16:37:12","2026-05-13 14:22:45",108.82122038842118,[132,133,134,135],"topic-match","same-kind","same-target","same-author",[26,137],"scripts",{"id":139,"uuid":140,"slug":141,"title":142,"description":143,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":144,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":145,"tags":146,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":148,"asset_kind":30,"target_tools":149,"install_mode":35,"entrypoint":150,"risk_profile":151,"dependencies":153,"verification":158,"agent_metadata":161,"agent_fit":173,"trust":180,"provenance":184,"created_at":186,"updated_at":187,"__relatedScore":188,"__relatedReasons":189,"__sharedTags":190},1153,"34a91e34-3701-11f1-9bc6-00163e2b0d79","pytorch-deep-learning-framework-research-production-34a91e34","PyTorch — The Deep Learning Framework for Research and Production","PyTorch is an open-source deep learning framework by Meta that provides tensor computation with GPU acceleration and automatic differentiation. Its dynamic computation graph and Pythonic API make it the dominant framework for AI research and increasingly for production.",73,[],[147],{"id":24,"name":25,"slug":26,"icon":27},"d6d068606a75c0f8a0a0298145987ff1e82a0686dc05ae899b00642380b903a2",[32,33,34],"SKILL.md",{"executes_code":28,"modifies_global_config":28,"requires_secrets":152,"uses_absolute_paths":59,"network_access":28},[],{"npm":154,"pip":155,"brew":156,"system":157},[],[],[],[],{"commands":159,"expected_files":160},[],[13],{"asset_kind":30,"target_tools":162,"install_mode":35,"entrypoint":150,"risk_profile":163,"dependencies":165,"content_hash":148,"verification":170},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":164,"uses_absolute_paths":59,"network_access":28},[],{"npm":166,"pip":167,"brew":168,"system":169},[],[],[],[],{"commands":171,"expected_files":172},[],[13],{"target":33,"score":174,"status":175,"policy":176,"why":177,"asset_kind":30,"install_mode":35},64,"needs_confirmation","confirm",[65,66,67,178,179,71],"policy confirm","risk_profile.uses_absolute_paths is true",{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":148,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":181,"review_status":76,"signals":183},[182],"uses_absolute_paths",[78,79],{"owner_uuid":9,"owner_name":10,"source_url":185,"content_hash":148,"visibility":18,"created_at":186,"updated_at":187},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fpytorch-deep-learning-framework-research-production-34a91e34","2026-04-13 14:22:54","2026-05-13 05:10:53",105.80384757959646,[132,133,134,135],[26,137],{"id":192,"uuid":193,"slug":194,"title":195,"description":196,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":197,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":198,"tags":199,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":201,"asset_kind":30,"target_tools":202,"install_mode":35,"entrypoint":203,"risk_profile":204,"dependencies":206,"verification":211,"agent_metadata":214,"agent_fit":226,"trust":228,"provenance":232,"created_at":234,"updated_at":235,"__relatedScore":236,"__relatedReasons":237,"__sharedTags":238},2270,"17fc76ff-42ba-11f1-9bc6-00163e2b0d79","kornia-differentiable-computer-vision-library-pytorch-17fc76ff","Kornia — Differentiable Computer Vision Library for PyTorch","Kornia is a differentiable computer vision library built on PyTorch that provides GPU-accelerated implementations of classical vision algorithms including geometric transforms, color conversions, filtering, feature detection, and augmentations, all with full autograd support for end-to-end learning.",126,[],[200],{"id":24,"name":25,"slug":26,"icon":27},"feeb560a0045f81199387cfaf5aa8cd9c0f7c8ba0d29b7029854a02e993890cf",[32,33,34],"Kornia Overview",{"executes_code":28,"modifies_global_config":28,"requires_secrets":205,"uses_absolute_paths":28,"network_access":28},[],{"npm":207,"pip":208,"brew":209,"system":210},[],[],[],[],{"commands":212,"expected_files":213},[],[203],{"asset_kind":30,"target_tools":215,"install_mode":35,"entrypoint":203,"risk_profile":216,"dependencies":218,"content_hash":201,"verification":223},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":217,"uses_absolute_paths":28,"network_access":28},[],{"npm":219,"pip":220,"brew":221,"system":222},[],[],[],[],{"commands":224,"expected_files":225},[],[203],{"target":33,"score":61,"status":62,"policy":63,"why":227,"asset_kind":30,"install_mode":35},[65,66,67,68,69,70,71],{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":201,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":229,"review_status":76,"signals":230},[],[231,78,79,80],"asset has usage views",{"owner_uuid":9,"owner_name":10,"source_url":233,"content_hash":201,"visibility":18,"created_at":234,"updated_at":235},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fkornia-differentiable-computer-vision-library-pytorch-17fc76ff","2026-04-28 12:24:05","2026-05-13 01:33:29",92.15570558143393,[132,133,134,135],[26,137],{"id":240,"uuid":241,"slug":242,"title":243,"description":244,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":245,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":246,"tags":247,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":249,"asset_kind":30,"target_tools":250,"install_mode":35,"entrypoint":251,"risk_profile":252,"dependencies":254,"verification":259,"agent_metadata":262,"agent_fit":274,"trust":276,"provenance":279,"created_at":281,"updated_at":282,"__relatedScore":283,"__relatedReasons":284,"__sharedTags":285},2496,"8a713b12-45bc-11f1-9bc6-00163e2b0d79","asset-8a713b12","fast.ai — Making Deep Learning Accessible to Everyone","A layered deep learning library built on PyTorch that provides high-level components for practitioners and researchers along with a proven teaching methodology.",58,[],[248],{"id":24,"name":25,"slug":26,"icon":27},"4aae75ce439d36b7838539926bfbd14c01de91ef368a4c41db31a286db424922",[32,33,34],"fast.ai Deep Learning Library",{"executes_code":28,"modifies_global_config":28,"requires_secrets":253,"uses_absolute_paths":28,"network_access":28},[],{"npm":255,"pip":256,"brew":257,"system":258},[],[],[],[],{"commands":260,"expected_files":261},[],[251],{"asset_kind":30,"target_tools":263,"install_mode":35,"entrypoint":251,"risk_profile":264,"dependencies":266,"content_hash":249,"verification":271},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":265,"uses_absolute_paths":28,"network_access":28},[],{"npm":267,"pip":268,"brew":269,"system":270},[],[],[],[],{"commands":272,"expected_files":273},[],[251],{"target":33,"score":61,"status":62,"policy":63,"why":275,"asset_kind":30,"install_mode":35},[65,66,67,68,69,70,71],{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":249,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":277,"review_status":76,"signals":278},[],[78,79,80],{"owner_uuid":9,"owner_name":10,"source_url":280,"content_hash":249,"visibility":18,"created_at":281,"updated_at":282},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-8a713b12","2026-05-02 08:19:10","2026-05-13 14:26:45",91.65627801746322,[132,133,134,135],[26,137]]