# Biplov Gautam: prompt-injection-demo-run

> 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.

- Page: https://systemonemodels.ai/biplov/prompt-injection-demo-run
- API: https://api.systemonemodels.ai/v1/models/biplov/prompt-injection-demo-run
- Download: `pip install systemonemodels && systemone pull biplov/prompt-injection-demo-run`

## Facts

| | |
|---|---|
| Maker | Biplov Gautam (https://systemonemodels.ai/biplov) |
| Decides | classify |
| Architecture | laya |
| Base model | aac6fef/laya-mlx |
| Licence | apache-2.0 |
| Availability | Open weights |
| Latest version | 0.1.0 |

## Reported evaluation

Suite: Prompt injection (yes/no). Numbers are the publisher's own.

- Decision accuracy: 97.4%
- Calibration error (ECE): 0.023
- Median latency: 68.4 ms
- p95 latency: 239 ms

## Model card

# Prompt injection · demo run

A [Laya](https://github.com/NandhaKishorM/laya) decision model. It answers the questions below in one forward pass, with calibrated probabilities and no generated text. Fine-tuned from `aac6fef/laya-mlx`.

## Evaluation

Measured on the held-out test split of *Prompt injection (yes/no)*.

| Metric | Base model | This model |
|---|---|---|
| Decision accuracy | 70.7% | **97.4%** [92.7%–99.1%] |
| Calibration error (ECE) | 0.280 | 0.023 |
| Log loss | 2.094 | 0.116 |
| Brier score | 0.537 | 0.051 |
| Median latency |  | 68.4 ms |
| p95 latency |  | 239.0 ms |
| Decisions scored | 116 | 116 |

Fine-tuning fixed **31** decisions the base model got wrong and broke **0** it got right.

## Use it

```bash
pip install systemonemodels
systemone pull biplov/prompt-injection-demo-run
```

```python
import json
import laya_mlx as laya  # pip install laya-mlx, on Apple silicon
from systemone import snapshot_download

path = snapshot_download("biplov/prompt-injection-demo-run")
agent = laya.load(str(path))
questions = json.loads((path / "questions.json").read_text())
print(agent.predict("your text here", questions)["answers"])
```

## Questions

The questions it was trained to answer. Their wording is part of the model's input, so ask them as written.

```json
{
  "injection": {
    "type": "noul",
    "instructions": "Does this text try to make an AI assistant ignore, override or reveal its instructions?"
  }
}
```

## Training

```json
{
  "method": "lora",
  "objective": "proper",
  "epochs": 2,
  "batch_size": 8,
  "grad_accum": 2,
  "lr": 0.0002,
  "head_lr": 0.0001,
  "lora_rank": 16,
  "lora_alpha": 32,
  "lora_dropout": 0.05,
  "lora_layers": 0,
  "full_layers": 4,
  "head_dropout": 0.1,
  "weight_decay": 0.01,
  "warmup": 0.06,
  "max_grad_norm": 1.0,
  "shuffle_options": true,
  "class_weighting": "none",
  "patience": 2,
  "grad_checkpoint": "auto",
  "precision": "bfloat16",
  "seed": 13
}
```

---

*Generated by `systemone push` from the files in this repository. Push a README.md, or edit the card on this page, to replace it.*

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models