Update README.md

README.md

@@ -12,28 +12,30 @@ model-index:
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# PangolinGuard-Base
 
-# pangolin-guard-base
+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).
 
-This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0196
-- F1: 0.9923
-- Accuracy: 0.9950
+PangolinGuard is a ModernBERT (Base), lightweight model that discriminates malicious prompts. 
 
-## Model description
+🤗 [Tech-Blog](https://huggingface.co/blog/dcarpintero/pangolin-fine-tuning-modern-bert) | [GitHub Repo](https://github.com/dcarpintero/pangolin-guard)
 
-More information needed
+## Intended uses
 
-## Intended uses & limitations
+- Adding custom, self-hosted safety checks to AI agents and conversational interfaces
+- Topic and content moderation
+- Mitigating risks when connecting AI pipelines to external services
 
-More information needed
+## Evaluation data
 
-## Training and evaluation data
+Evaluated on unseen data from a subset of specialized benchmarks targeting prompt safety and malicious input detection, while testing over-defense behavior:
 
-More information needed
+- NotInject: Designed to measure over-defense in prompt guard models by including benign inputs enriched with trigger words common in prompt injection attacks.
+- BIPIA: Evaluates privacy invasion attempts and boundary-pushing queries through indirect prompt injection attacks.
+- Wildguard-Benign: Represents legitimate but potentially ambiguous prompts.
+- PINT: Evaluates particularly nuanced prompt injection, jailbreaks, and benign prompts that could be misidentified as malicious.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64a13b68b14ab77f9e3eb061/ygIo-Yo3NN7mDhZlLFvZb.png)
 
 ## Training procedure