NVIDIA skills collection

Tao Finetune Clip

CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment.

Tao Finetune Cosmos Embed

Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning.

Tao Finetune Cosmos Reason

Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH or packaged backend image, optionally plans explicit clean source builds, prepares…

Tao Finetune Huggingface Model

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches.

Tao Finetune Nv Tesseract Ad Diffusion

NV-Tesseract AD Diffusion — diffusion-based anomaly detection and fine-tuning for multivariate time series.

Tao Finetune Nv Tesseract Forecasting

NV-Tesseract Forecasting — transformer-based multivariate time series forecasting with DARR (context-enhanced kNN retrieval), interpretability, and fine-tuning.

Tao Finetune Video Clip

InternVideo2-CLIP L14 (TAO videoclip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment.

Tao Generate Anomalies

Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nnscore), and search per-sample (guidance, cropratio) parameters. Three modes: full (Phase 0→7: finetune then…

Tao Generate Image Embeddings

Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint.

Tao Generate Image Grounding

Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM.

Tao Generate Referring Expressions

Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation.

Tao Generate Video Reasoning Annotations

Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation.

Tao Launch Workflow

Check launch prerequisites and execute NVIDIA TAO workflows for training, evaluation, inference, export, and TensorRT engine generation.

Tao List Capabilities

Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests.

Tao Mine Aoi Images

Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour source images for downstream augmentation. Use as the immediate next step after…

Tao Mine Nearest Neighbors

Run TAO Data Services TMM nearest-neighbor mining from embedding parquet files.

Tao Mine Od Images

Run TAO Data Services TMM unique-neighbor matching mining from embedding parquet files for object detection workflows.

Tao Port Huggingface Model

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).

Tao Route Visual Changenet Samples

Routes the weakest VCN samples (output of tao-analyze-gaps-visual-changenet) into per-augmentation-module subsets based on each module's label eligibility.

Tao Run Automl

Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution…