Token Classification
TensorRT
ONNX
Russian
bert
cuda
cuda-graphs
fp16
pii
ner
named-entity-recognition
russian
Eval Results (legacy)
Instructions to use lockR/rubert-base-pii-ner-tensorrt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use lockR/rubert-base-pii-ner-tensorrt with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download build_metadata.json from lockR/rubert-base-pii-ner-tensorrt: direct link, hf CLI and curl.
- Browser
- Download file 629 Bytes
-
https://huggingface.co/lockR/rubert-base-pii-ner-tensorrt/resolve/main/build_metadata.json
- Command line
-
hf download hf://lockR/rubert-base-pii-ner-tensorrt/build_metadata.json
-
curl -L -o build_metadata.json https://huggingface.co/lockR/rubert-base-pii-ner-tensorrt/resolve/main/build_metadata.json
629 Bytes
| { | |
| "tensorrt": "10.13.3.9", | |
| "torch": "2.8.0+cu128", | |
| "cuda": "12.8", | |
| "gpu": "NVIDIA GeForce RTX 4070 Ti SUPER", | |
| "compute_capability": [ | |
| 8, | |
| 9 | |
| ], | |
| "onnx": "model.onnx", | |
| "onnx_sha256": "fa8775d59ef345d7934fb7a01671fbe24c5c098c0e44dcc397a67af6c5a4805b", | |
| "precision": "FP16 with FP32 normalization accumulation; TF32 disabled", | |
| "normalization_layers": 25, | |
| "profile": { | |
| "min": [ | |
| 1, | |
| 2 | |
| ], | |
| "opt": [ | |
| 1, | |
| 128 | |
| ], | |
| "max": [ | |
| 32, | |
| 512 | |
| ] | |
| }, | |
| "workspace_gib": 4, | |
| "optimization_level": 3, | |
| "build_seconds": 25.086677140003303, | |
| "engine_bytes": 358632804 | |
| } | |