Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
Adds Liger Kernel support for a new HuggingFace Transformers model, or modifies existing monkey-patching. Generates lce_forward, monkey-patch function, tests, and README entry. Use when adding a new model to Liger Kernel, when a user asks to patch an unsupported model, when extending MODEL_TYPE_TO_APPLY_LIGER_FN, or when modifying/updating/fixing an existing monkey-patch (e.g., adding a new kernel to an already-supported model, fixing instance patching, updating a patch for upstream HF changes).
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative Gemini review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
Scaffold a new RemoteCompose wear material3 component with test, sample, and preview
Post-implementation verification across multiple code dimensions: cross-layer data flow, code reuse analysis, import path validation, and same-layer consistency checks. Identifies missed update sites, type mismatches, and duplicated constants. Use when changes span 3+ architectural layers, after modifying shared constants or configs, after batch file modifications, or when creating new utility functions.
Guide for adding a new model to the Archon engine. Use when user wants to add support for a new HuggingFace model architecture in ArchonEngine.
Guide for adding a new model to the Archon engine. Use when user wants to add support for a new HuggingFace model architecture in ArchonEngine.
Guide for debugging distributed training issues in AReaL. Use when user encounters hangs, wrong results, OOM, or communication errors.
Guide for adding a new model to the Archon engine. Use when user wants to add support for a new HuggingFace model architecture in ArchonEngine.
Resilient multi-tier PDF extraction with sequential fallback strategies when initial reading fails
Adaptive polling pattern with exponential backoff on failure, automatic recovery on success, and visibility-aware scheduling
Add new AI models to Kiln's ml_model_list.py and produce a Discord announcement. Use when the user wants to add, integrate, or register a new LLM model (e.g. Claude, GPT, DeepSeek, Gemini, Kimi, Qwen, Grok) into the Kiln model list, mentions adding a model to ml_model_list.py, or asks to discover/find new models that are available but not yet in Kiln.
Build a systematic threat hunt hypothesis framework that transforms threat intelligence, attack patterns, and environmental data into testable hunting hypotheses.
