QwenCollection/walledguard-c
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Cherrytest
2025-09-18 10:05:58 +00:00
parent 395bd7fa64
commit 45b537fe63
1 changed files with 6 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@@ -25,19 +25,13 @@ widget:
<!-- Provide a quick summary of what the model is/does. --> <!-- Provide a quick summary of what the model is/does. -->
- 🔥📣 **WalledProtect** is the most capable content moderator of Walled AI to date. To try the latest version, get your free API access at [**www.walled.ai**](https://app.walled.ai/login). Read the full announcement at [**blog**](https://blog.walled.ai/introducing-walledprotect/). - 🔥**WalledGuard** comes in two versions: **Community** and **Advanced***.
- 🔥**WalledGuard** comes in two versions: **Community** and **Advanced***. - 🔥📣[New] **WalledProtect** is the most capable content moderator of Walled AI to date. To try the latest version, get your free API access at [**www.walled.ai**](https://app.walled.ai/login). Read the full announcement at [**blog**](https://blog.walled.ai/introducing-walledprotect/).
- 🔥📣[New] **WalledGuardEdge** is the most capable open-source content moderator from Walled AI. Try it here: [**WalledGuard-Edge**](https://huggingface.co/walledai/walledguard-edge).
- 🔥 Please check out our LLM Safety Evaluation One-Stop Center: [**Walled Eval**](https://github.com/walledai/walledeval)!
_Note: The Advanced version is now named as WalledProtect. Get your free API access at [**www.walled.ai**](https://app.walled.ai/login). Latest scores can be found [**here**](https://huggingface.co/walledai/walledguard-edge)._
<small>(*_More performant, suitable for enterprise use_)</small>
<span style="color: blue;">_Note: We also provide customized guardrails for enterprise-specific use cases, please reach out to us at [**www.walled.ai**](https://www.walled.ai/)._</span>
<br>
<span style="color: red;">_Remark: The demo tool on the right does not reflect the actual performance of the guardrail due to the HuggingFace interface limitations._</span>
## Model Details ## Model Details
@@ -147,6 +141,8 @@ print(prediction)
**Table**: Scores on [DynamoBench](https://huggingface.co/datasets/dynamoai/dynamoai-benchmark-safety?row=0), [XSTest](https://huggingface.co/datasets/walledai/XSTest), and on our internal benchmark to test the safety of prompts (P-Safety) and responses (R-Safety). We report binary classification accuracy. **Table**: Scores on [DynamoBench](https://huggingface.co/datasets/dynamoai/dynamoai-benchmark-safety?row=0), [XSTest](https://huggingface.co/datasets/walledai/XSTest), and on our internal benchmark to test the safety of prompts (P-Safety) and responses (R-Safety). We report binary classification accuracy.
_Note: The Advanced version is now named as WalledProtect. Get your free API access at [**www.walled.ai**](https://app.walled.ai/login). Latest scores can be found [**here**](https://huggingface.co/walledai/walledguard-edge)._
## LLM Safety Evaluation Hub ## LLM Safety Evaluation Hub
Please check out our LLM Safety Evaluation One-Stop Center: [**Walled Eval**](https://github.com/walledai/walledeval)! Please check out our LLM Safety Evaluation One-Stop Center: [**Walled Eval**](https://github.com/walledai/walledeval)!