Commit History
4 days ago
-
Superseded: remove release files from PR #1
Verified signatureFile names and configuration files carried training details. Replaced by a new pull request with a neutral layout.e8a5f53 -
Add InternVideo2-CLIP-anomaly-detection v1.0 (TAO fine-tune, research release)
Verified signatureAdds the InternVideo2-CLIP-anomaly-detection v1.0 release files: the TAO `video_clip` fine-tune of OpenGVLab InternVideo2-CLIP-L14 (vision LoRA on the last 12 blocks, frozen MobileCLIP-B-LT text encoder, preservation regularization) trained on the PhysicalAI-Event-Videos train subset, released for non-commercial research under the NVIDIA Internal Scientific Research and Development Model License already set on this repository. **Contents (19 files, 4.9 GB)** - `model.safetensors` — fine-tuned weights with the 24 LoRA modules merged (486 tensors, 372,752,643 parameters, FP32, TAO state-dict key names) + `model_config.yaml`. - `model_epoch_002_step_04011.no_teacher.pth` — TAO checkpoint, LoRA unmerged, teacher/optimizer state removed + `train_experiment.yaml`. - `onnx_opset23/` — FP32 vision and text towers (opset 23, dynamic batch, `.onnx` + `.onnx.data`), ModelOpt AutoCast FP16 towers for strongly typed TensorRT builds, deploy config, export spec, CLIP BPE tokenizer. - `README.md` — m…bc9bbb0 -
initial commit
Verified signature4a05252
