Agent skill · NVIDIA
tao-finetune-clip
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX
What it needs
About 7k tokens when loaded.
What this skill does
CLIP Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery). Contrastive Language-Image Pre-training model for zero-shot and fine-tuned image classification, image-text retrieval, and embedding extraction. Fine-tuning adapts CLIP's shared image-text embedding space to domain-specific image-caption data. No default NGC pretrained checkpoint is required for spec construction, but unset checkpoint behavior is action-specific. In the validation-fixes PyTorch image, export.checkpoint: null exports the selected CLIP architecture and may initialize weights when pretrained weights are unavailable. Do not assume inference.checkpoint: null loads pretrained weights: clip inference currently calls the checkpoint loader with None and fails before embedding extraction. For PyTorch inference, checkpoint-backed evaluation/export, resume, and retrain flows, resolve and pass an exact checkpoint from the parent train output. For trusted TAO checkpoints produced by the current run or a known parent job, set TORCHFORCENOWEIGHTSONLYLOAD=1 on checkpoint-dependent PyTorch actions so PyTorch 2.6 can load the Lightning checkpoint metadata; do not set this for untrusted checkpoints. Supported actions: train, evaluate, inference, export, gentrtengine. Train Action Policy This model is AutoML-enabled at the model layer. Before handling any train-stage request, read references/skillinfo.yaml and resolve the run override from either an explicit automlpolicy value or the user's workflow request. Use automlpolicy: on by default and only expose on / off in new launch prompts. Treat phrases like "turn off AutoML", "disable AutoML", "no HPO", or "plain training" as automlpolicy: off for this run only. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills NVIDIA/tao-finetune-clip