Add model card

README.md

@@ -0,0 +1,92 @@
+---
+language:
+- en
+license: mit
+tags:
+- prompt-injection
+- security
+- classification
+- fine-tuned
+- myfi
+datasets:
+- custom
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+- auc
+---
+
+# Fine-tuned Llama-Prompt-Guard-2-86M
+
+This is a fine-tuned version of the Meta Llama-Prompt-Guard-2-86M model for prompt injection detection, developed by the MyFi team.
+
+## Model Description
+
+- **Base Model**: meta-llama/Llama-Prompt-Guard-2-86M
+- **Task**: Binary classification (benign vs malicious prompts)
+- **Architecture**: mDeBERTa-base with custom classifier head
+- **Fine-tuning**: Custom dataset with balanced benign/malicious samples
+- **Organization**: MyFi
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+model_name = "myfi/llama-prompt-guard-finetuned"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Classify text
+text = "How do I hack a computer?"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
+outputs = model(**inputs)
+
+# Apply temperature scaling (recommended: 3.0)
+temperature = 3.0
+scaled_logits = outputs.logits / temperature
+probabilities = torch.softmax(scaled_logits, dim=-1)
+
+# Get prediction
+benign_prob = probabilities[0][0].item()
+malicious_prob = probabilities[0][1].item()
+prediction_result = "MALICIOUS" if malicious_prob > 0.5 else "BENIGN"
+
+print(f"Prediction: {prediction_result}")
+print(f"Benign Probability: {benign_prob:.4f}")
+print(f"Malicious Probability: {malicious_prob:.4f}")
+```
+
+## Training Details
+
+- **Dataset**: Custom dataset with balanced benign/malicious samples
+- **Training Method**: Fine-tuning with custom loss function
+- **Temperature Scaling**: Recommended temperature = 3.0
+- **Classification Threshold**: Default = 0.5
+- **Organization**: MyFi
+
+## Performance
+
+The model is designed to detect prompt injection attempts and malicious queries while allowing legitimate requests to pass through.
+
+## Limitations
+
+- May have false positives/negatives on edge cases
+- Performance depends on the quality and distribution of training data
+- Should be used as part of a broader security strategy
+
+## License
+
+This model is licensed under the MIT License.
+
+## Organization
+
+This model is maintained by [MyFi](https://huggingface.co/myfi) - a company focused on AI & ML solutions.
+
+## Citation
+
+If you use this model, please cite the original Llama-Prompt-Guard-2-86M paper and mention that this is a fine-tuned version by MyFi.