GitHub
plan-mode-arc-gsm8k-improvement
AEGISモデルのARC-Challenge評価改善とGSM8K健全性チェックのためのPlanモード。タイムアウト率・抽出失敗率分析、頑健な回答抽出、データ汚染検査、複数seed評価を実行。
zapabob AI Skills
GitHub ↗Explorez les skills IA publiés de zapabob et consultez leurs instructions source.
Statistiques de l’auteur
Skills indexés
14Étoiles des dépôts des skills indexés
0Forks du dépôt
0Moyenne des étoiles par skill indexé
0Les étoiles d’un dépôt peuvent se répéter entre ses skills.
Catégories populaires
Indexation récente
Explorer
GitHub
plan-mode-aegis-v25-development
AEGIS v2.5開発の包括的Planモード。数学データ収集、形式証明環境構築、GRPO訓練パイプライン、MCP/A2Aエージェント開発、進捗監視を実装。SO(8)四重推論再現のための完全開発ワークフロー。
GitHub
plan-mode
AEGISモデルのARC-Challenge改善、GSM8K健全性検証、GRPO報酬多目的化のための包括的Planモード。頑健な回答抽出、タイムアウト最適化、データ汚染チェック、複数seed評価、汎化性能向上を実装。
GitHub
plan-mode-creation
Planモードの設計・作成・設定を自動化するスキル。AI開発ワークフローのPlanモードを効率的に構築し、チェックポイント管理・進捗監視・エラー回復機能を統合。SO8Tプロジェクト専用に最適化。
GitHub
plan-mode-official-leaderboard-abctest
公式リーダーボード準拠のA/B/Cテストを実行するPlanモードスキル。Phi-3.5-mini-instruct、Borea-phi3.5-instinct-jp、AEGIS-Phi3.5mini-jpv2.4を標準化ベンチマークで比較評価し、統計的有意性を検証。
GitHub
plan-mode-advanced
Create and execute advanced execution plans for complex AI model development incorporating 2024-2026 cutting-edge techniques (DeepSeek GRPO, manifold-constrained architectures, geometric scaling). Use when plan...
GitHub
mathematical-theorem-prover
Implement comprehensive mathematical theorem proving capabilities with SFT+GRPO training, MCP/A2A agent integration, and imatrix quantization protection to surpass Boreas-phi3.5-instinct-jp in formal proof gene...
GitHub
quantization-evaluation-pipeline
Execute GGUF quantization with imatrix protection, perform statistical benchmark evaluation with error bars, generate academic-style methodology documentation, and create comprehensive scorecards. Use when eval...
GitHub
sunset-pipeline-moonshot-integration
Integrate Moonshot AI pipeline best practices for dataset collection, labeling, cleansing, quadrality inference thinking model development, rolling stock power management, and industry-standard benchmarking wit...
GitHub
sunset-pipeline-rtx3060-optimized
Optimize Sunset Pipeline Moonshot Integration for 32GB RAM + RTX 3060 GPU environment with practical scaling, resource-efficient implementations, and achievable milestones. Use when implementing AI development...
GitHub
so8t-nobel-fields-inference
Enable Nobel Prize and Fields Medal level mathematical reasoning and breakthrough capabilities in SO8T models through alpha gate sigmoid control, golden ratio phi^(-2) convergence, and induced grokking phenomen...
GitHub
so8t-thinking-plan-mode
Develop comprehensive evolution plan for Qwen2.5-7B to SO8T/thinking model with advanced Japanese capabilities, mathematical reasoning at Nobel/Fields medal level, and integration of 2024-2026 LLM breakthroughs...
GitHub
sunset-pipeline-integration
Integrate DeepSeek-R1 GRPO, mHC manifold constraints, geometric scaling, and SO8T quadrality inference into Sunset Pipeline for advanced LLM evolution. Use when implementing cutting-edge mathematical reasoning...
GitHub
sunset-pipeline-plan-mode
Create comprehensive implementation plans for integrating GRPO, mHC manifold constraints, geometric scaling, SO8T quadrality inference, and imatrix quantization into Sunset Pipeline for advanced LLM evolution....
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.