Loading…
Loading…
Models / deberta-v3-small / deberta-v3-small
Classification · served with ONNX Runtime · ↓ 4.8K downloads a month · View on Hugging Face
protectai/deberta-v3-small-prompt-injection-v2 needs about 1.9 GB of GPU memory. It runs on one GTX 1650 from $0.06/h right now; best value: RTX 5090 at $0.56/h.
The model's publisher asks users to accept its licence (apache-2.0). GridPup cannot download this one yet: choose an ungated version below.
The same model packaged differently: a quantized version needs less GPU memory and runs on a cheaper machine.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Main (cross-encoder)cross-encoder/nli-deberta-v3-small | ONNX Runtime | 170 MB | 1.3 GB | $0.06/h GTX 1650 |
| prompt injection v2 (protectai)protectai/deberta-v3-small-prompt-injection-v2Licence to accept | ONNX Runtime | 570 MB | 1.9 GB | $0.06/h GTX 1650 |
The publisher has not let GridPup download this licence-gated model yet. An ungated version of it (above) can be deployed.
Prices are per hour for the whole machine and its disk, right now. Speed is Vast's DLPerf score of the machine, relative to the cheapest. Best value: the most speed per dollar. Only machines with a Vast reliability above 95% that download at 400 Mbit/s or more are offered: the machine fetches the model itself.