domains / families / science / tao-finetune-video-clip

tao-finetune-video-clip

separate

InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment. Use when the user asks to "fine-tune IV2CLIP", "run video_clip train/evaluate/inference/export", "build a Video-CLIP TensorRT engine", "InternVideo2-CLIP on KPI chunks", or "TAO video_clip on vadr1_chunks JSON".

When to use

• fine-tune IV2CLIP
• run video_clip train/evaluate/inference/export
• build a Video-CLIP TensorRT engine
• InternVideo2-CLIP on KPI chunks
• TAO video_clip on vadr1_chunks JSON
• video-text retrieval
• zero-shot classification
• embedding extraction

When not to use

• AutoML

Skill page

Source