All models
COMPARE
Put models side by side.
What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.
| Property | biplov/prompt-injection-demo-run |
|---|---|
| Summary | Prompt injection · demo run. Does this text try to make an AI assistant ignore, override or reveal its instructions? Fine-tuned from aac6fef/laya-mlx. |
| Decides | classify |
| Architecture | laya |
| Fine-tuned from | aac6fef/laya-mlx |
| License | apache-2.0 |
| Decision accuracy | 97.4% |
| Calibration error | 0.023 |
| Valid action rate | — |
| Median latency | 68.4 ms |
| p95 latency | 239 ms |
| Evaluation suite | Prompt injection (yes/no) |
| Latest version | 0.1.0 |
| Variants | encoder, tokenizer |
| Size of latest version | 807.0 MB |
| Files | 7 |
| Downloads | 0 |
| Stars | 0 |
| Tags | mlx |
| Updated | Sep 24, 2026 |