Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ model-index:
|
|
| 16 |
|
| 17 |
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).
|
| 18 |
|
| 19 |
-
PangolinGuard is a ModernBERT (Base), lightweight model that discriminates malicious prompts.
|
| 20 |
|
| 21 |
🤗 [Tech-Blog](https://huggingface.co/blog/dcarpintero/pangolin-fine-tuning-modern-bert) | [GitHub Repo](https://github.com/dcarpintero/pangolin-guard)
|
| 22 |
|
|
|
|
| 16 |
|
| 17 |
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).
|
| 18 |
|
| 19 |
+
PangolinGuard is a ModernBERT (Base), lightweight model that discriminates malicious prompts (i.e. prompt injection attacks).
|
| 20 |
|
| 21 |
🤗 [Tech-Blog](https://huggingface.co/blog/dcarpintero/pangolin-fine-tuning-modern-bert) | [GitHub Repo](https://github.com/dcarpintero/pangolin-guard)
|
| 22 |
|