
Runs InternVideo2-CLIP video-text retrieval, fine-tuning, ONNX export and TensorRT deploy
- Open source
- 4K GitHub stars
- Design and media


Runs InternVideo2-CLIP video-text retrieval, fine-tuning, ONNX export and TensorRT deploy

Runs an iterative retrain-and-evaluate loop to improve NVIDIA TAO CLIP image-text

Trains, distills, quantizes and runs RT-DETR real-time object detection models

Runs Cosmos-Embed1 video-text embedding for search, dedup and fine-tuning in Docker

Computes image embeddings from a parquet of file paths using CLIP, SigLIP or TAO

Trains, evaluates, exports and runs NVIDIA TAO Deformable DETR object detectors

Trains, evaluates and exports TAO Sparse4D multi-camera 3D detection and tracking models

Fine-tunes HuggingFace vision, VLM and LLM models in an NVIDIA GPU container

Trains, evaluates, exports and runs DINO 2D object detectors via TAO in Docker

Runs a standard TAO train, evaluate and export sequence without AutoML loops

Chains AutoML tuning, a DEFT data-improvement loop and a final AutoML pass for PCB AOI

Guides an agent to port a HuggingFace vision model into the NVIDIA TAO Toolkit
The closest alternatives to Tao finetune clip are Tao finetune video clip, Tao run deft pas, Tao train rtdetr, Tao finetune cosmos embed and Tao generate image embeddings.
Yes. Tao finetune video clip, Tao run deft pas, Tao train rtdetr have a free or open-source option.