Loading...
Loading...
Found 21 Skills
Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, ingestion of customer-supplied pre-generated AnomalyGen images, k-NN mining, retraining, and deployment gating until FAR / recall KPI targets are met. EA variant — does not run AnomalyGen inline; the customer pre-generates synthetic NG/OK pairs out-of-band and the loop ingests them. Use for prompts like "run the DEFT loop", "fine-tune until FAR below 0.1% at recall=100%", or "improve my AOI ChangeNet model with RCA and pre-generated synthetic defects"; do not use for standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.
Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a cheaper model, stop depending on one vendor, compare models side-by-side, a model update broke your outputs, you need vendor diversification, or you want to migrate to a local model. Covers DSPy model portability — provider config, re-optimization, model comparison, and multi-model pipelines.
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to "integrate a HuggingFace model into TAO", "add an HF model to TAO Toolkit", "wire a HuggingFace ViT/DETR/ SegFormer into tao-pytorch", "build a TAO trainer + deploy pipeline for an HF CV model", or pastes a HuggingFace model URL/ID and wants it turned into a TAO model. Covers the full 7-phase loop: prerequisites check, HuggingFace inspection and validation, codebase exploration, tao-core configuration and native trainer implementation, ONNX export plus TensorRT deploy integration, packaging and L0 testing, container-based end-to-end validation, and (conditional) accuracy/latency tuning. Supports classification, object detection, semantic / instance / panoptic segmentation, zero-shot detection, and depth estimation.
Power BI semantic modeling assistant for building optimized data models. Use when working with Power BI semantic models, creating measures, designing star schemas, configuring relationships, implementing RLS, or optimizing model performance. Triggers on queries about DAX calculations, table relationships, dimension/fact table design, naming conventions, model documentation, cardinality, cross-filter direction, calculation groups, and data model best practices. Always connects to the active model first using power-bi-modeling MCP tools to understand the data structure before providing guidance.
Design AI architectures, write Prompts, build RAG systems and LangChain applications
Use when user needs ML model deployment, production serving infrastructure, optimization strategies, and real-time inference systems. Designs and implements scalable ML systems with focus on reliability and performance.
Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.
Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks. Invoke for parameter-efficient methods, dataset preparation, or model adaptation.
Use when an SGLang, vLLM, or TensorRT-LLM serving/model optimization task needs prior model-family PR evidence. Query and read the PR-driven history docs under model-pr-optimization-history before choosing source paths, fast paths, kernel/fusion ideas, regression risks, or validation lanes.
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.