Update README.md

README.md

@@ -3,7 +3,9 @@ library_name: transformers
 license: apache-2.0
 base_model: answerdotai/ModernBERT-base
 tags:
-- generated_from_trainer
+- ai-safety
+- safeguards
+- guardrails
 metrics:
 - f1
 - accuracy
@@ -16,15 +18,15 @@ model-index:
 
 LLM applications face critical security challenges in form of prompt injections and jailbreaks. This can result in models leaking sensitive data or deviating from their intended behavior. Existing safeguard models are not fully open and have limited context windows (e.g., only 512 tokens in LlamaGuard).
 
-PangolinGuard is a ModernBERT (Base), lightweight model that discriminates malicious prompts (i.e. prompt injection attacks). 
+**Pangolin Guard** is a ModernBERT (Base), lightweight model that discriminates malicious prompts (i.e. prompt injection attacks). 
 
 🤗 [Tech-Blog](https://huggingface.co/blog/dcarpintero/pangolin-fine-tuning-modern-bert) | [GitHub Repo](https://github.com/dcarpintero/pangolin-guard)
 
-## Intended uses
+## Intended Use Cases
 
-- Adding a self-hosted, inexpensive safety checks (against prompt injection attacks) to AI agents and conversational interfaces.
+- Adding a self-hosted, inexpensive defense mechanism against prompt injection attacks to AI agents and conversational interfaces.
 
-## Evaluation data
+## Evaluation Data
 
 Evaluated on unseen data from a subset of specialized benchmarks targeting prompt safety and malicious input detection, while testing over-defense behavior:
 
@@ -35,9 +37,20 @@ Evaluated on unseen data from a subset of specialized benchmarks targeting promp
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64a13b68b14ab77f9e3eb061/ygIo-Yo3NN7mDhZlLFvZb.png)
 
-## Training procedure
 
-### Training hyperparameters
+## Inference
+
+```python
+from transformers import pipeline
+
+classifier = pipeline("text-classification", "dcarpintero/pangolin-guard-base")
+text = "your input text"
+output = classifier(text)
+```
+
+## Training Procedure
+
+### Training Hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
@@ -48,7 +61,7 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 2
 
-### Training results
+### Training Results
 
 | Training Loss | Epoch  | Step | Validation Loss | F1     | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:------:|:--------:|
@@ -78,4 +91,4 @@ The following hyperparameters were used during training:
 - Transformers 4.50.0
 - Pytorch 2.6.0+cu124
 - Datasets 3.4.1
-- Tokenizers 0.21.1
+- Tokenizers 0.21.1