Loading...
Loading...
Found 75 Skills
Build identity-preserving character generation workflows and pipelines in ComfyUI. Selects the optimal identity method (InfiniteYou, FLUX Kontext, PuLID, InstantID, IP-Adapter) based on use case requirements. Handles face preservation, likeness transfer, cross-domain conversion (3D to photo), multi-reference consistency, iterative character editing, and character variation generation. Triggers on requests to generate consistent characters, preserve identity across images, create face-swapping workflows, or convert 3D renders to photorealistic portraits. Does NOT cover general image generation without identity preservation, model training/LoRA fine-tuning, animation, technical explanations, or workflow debugging.
Configure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptation
Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API, fine-tuning models with Trainer, or handling text, vision, audio, and multimodal tasks.
Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, vision-language models, and both high-level Cookbook patterns and low-level API usage.
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.
Guides ML/research engineering for safeguards—safety classifier development, harm benchmarks and eval suites, labeled dataset design, fine-tuning and ablations, calibration and slice analysis, attack-surface research memos, and promotion criteria for new moderation models. Use when building or evaluating guardrail models, designing safety benchmarks, measuring precision/recall on policy categories, comparing mitigation techniques, or writing research reports on classifier improvements—not for production inference gateways (ml-infrastructure-engineer-safeguards), PII/leakage privacy research (privacy-research-engineer-safeguards), red-team attack campaigns (ai-redteam), AI governance policy (ai-risk-governance), general non-safety research (ai-researcher), or token-efficiency studies (research-engineer-scientist-tokens).
Guidance for recovering PyTorch model architectures from state dictionaries, retraining specific layers, and saving models in TorchScript format. This skill should be used when tasks involve reconstructing model architectures from saved weights, fine-tuning specific layers while freezing others, or converting models to TorchScript format.
Reduce your AI API bill. Use when AI costs are too high, API calls are too expensive, you want to use cheaper models, optimize token usage, reduce LLM spending, route easy questions to cheap models, or make your AI feature more cost-effective. Covers DSPy cost optimization — cheaper models, smart routing, per-module LMs, fine-tuning, caching, and prompt reduction.
Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support