Rakancorle1
/

PolicyGuard-4B

Text Classification

text-generation

text-generation-inference

Model card Files Files and versions

Rakancorle1 commited on Oct 9

Commit

03f2cfb

·

verified ·

1 Parent(s): 08b62e5

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -50,10 +50,10 @@ Built on the **PolicyGuardBench** dataset, it achieves **high accuracy**, **cros
 | Model | Type | Params | Accuracy | F1 | Latency (ms/example) |
 |:------|:------|:-------:|:---------:|:----:|:--------------------:|
-| **PolicyGuard-4B (ours)** | Guardrail | 4B | **0.9014** | **0.8759** | **22.5** |
 | Llama-Guard-3-8B | Guardrail | 8B | 0.4246 | 0.5952 | 164.8 |
 | Qwen-3-8B | Foundation | 8B | 0.6408 | 0.6407 | 115.8 |
-| Llama-3.3-70B | Foundation | 70B | 0.9054 | 0.8883 | 305.0 |
 | Gemini-1.5-Pro | Frontier | – | 0.8713 | 0.8502 | 596.1 |
 ➡️ **PolicyGuard-4B** achieves **near-frontier accuracy** at **<1/10 inference cost**, demonstrating that efficient, small-scale guardrails are feasible:contentReference[oaicite:1]{index=1}.

 | Model | Type | Params | Accuracy | F1 | Latency (ms/example) |
 |:------|:------|:-------:|:---------:|:----:|:--------------------:|
+| **PolicyGuard-4B (ours)** | Guardrail | 4B | <u>0.9014</u> | <u>0.8759</u> | **22.5** |
 | Llama-Guard-3-8B | Guardrail | 8B | 0.4246 | 0.5952 | 164.8 |
 | Qwen-3-8B | Foundation | 8B | 0.6408 | 0.6407 | 115.8 |
+| Llama-3.3-70B | Foundation | 70B | **0.9054** | **0.8883** | 305.0 |
 | Gemini-1.5-Pro | Frontier | – | 0.8713 | 0.8502 | 596.1 |
 ➡️ **PolicyGuard-4B** achieves **near-frontier accuracy** at **<1/10 inference cost**, demonstrating that efficient, small-scale guardrails are feasible:contentReference[oaicite:1]{index=1}.