davidberenstein1957 commited on
Commit
29a0150
·
verified ·
1 Parent(s): af5fe41

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -33
README.md CHANGED
@@ -22,36 +22,36 @@ Below is an overview of all guardrails showing best results for smallest (-2m),
22
 
23
  | Dataset | Classifies | Collection | Smallest (2m) | Best Performing | Multi-lingual (128m) |
24
  | --- | --- | --- | --- | --- | --- |
25
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | general-safety-education-binary | [Collection](https://huggingface.co/collections/enguard/general-safety-education-binary-guardset-690b96092286c0e2c3b8a238) | [0.9431](https://huggingface.co/enguard/tiny-guard-2m-en-general-safety-education-binary-guardset) | [0.9544](https://huggingface.co/enguard/small-guard-32m-en-general-safety-education-binary-guardset) | [0.9419](https://huggingface.co/enguard/medium-guard-128m-xx-general-safety-education-binary-guardset) |
26
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | response-safety-cyber-binary | [Collection](https://huggingface.co/collections/enguard/response-safety-cyber-binary-guardset-690b9610479d2f239f958756) | [0.8926](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-cyber-binary-guardset) | [0.9225](https://huggingface.co/enguard/small-guard-32m-en-response-safety-cyber-binary-guardset) | [0.9268](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-cyber-binary-guardset) |
27
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-response-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-response-safety-binary-guardset-690b960c0326245fed30b069) | [0.9136](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-response-safety-binary-guardset) | [0.9339](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-response-safety-binary-guardset) | [0.9416](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-response-safety-binary-guardset) |
28
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-safety-finance-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-finance-binary-guardset-690b960ea52bbafc766f3058) | [0.9887](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-finance-binary-guardset) | [0.9944](https://huggingface.co/enguard/small-guard-32m-en-prompt-safety-finance-binary-guardset) | [0.9958](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-finance-binary-guardset) |
29
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | general-safety-hr-binary | [Collection](https://huggingface.co/collections/enguard/general-safety-hr-binary-guardset-690b960aa52bbafc766f2fff) | [0.9313](https://huggingface.co/enguard/tiny-guard-2m-en-general-safety-hr-binary-guardset) | [0.9595](https://huggingface.co/enguard/small-guard-32m-en-general-safety-hr-binary-guardset) | [0.9506](https://huggingface.co/enguard/medium-guard-128m-xx-general-safety-hr-binary-guardset) |
30
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-safety-law-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-law-binary-guardset-690b960f682fe55899d4ac74) | [0.9345](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-law-binary-guardset) | [0.9673](https://huggingface.co/enguard/small-guard-32m-en-prompt-safety-law-binary-guardset) | [0.9405](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-law-binary-guardset) |
31
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-binary-guardset-690b960d682fe55899d4ac45) | [0.9295](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-binary-guardset) | [0.9349](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-safety-binary-guardset) | [0.9510](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-binary-guardset) |
32
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | response-safety-law-binary | [Collection](https://huggingface.co/collections/enguard/response-safety-law-binary-guardset-690b9612682fe55899d4acae) | [0.8590](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-law-binary-guardset) | [0.8590](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-law-binary-guardset) | [0.8508](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-law-binary-guardset) |
33
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | response-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-response-safety-binary-guardset-690b960c0326245fed30b069) | [0.8868](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-binary-guardset) | [0.9114](https://huggingface.co/enguard/small-guard-32m-en-response-safety-binary-guardset) | [0.9037](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-binary-guardset) |
34
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-safety-cyber-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-cyber-binary-guardset-690b960d0326245fed30b089) | [0.9052](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-cyber-binary-guardset) | [0.9305](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-safety-cyber-binary-guardset) | [0.9193](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-cyber-binary-guardset) |
35
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | response-safety-finance-binary | [Collection](https://huggingface.co/collections/enguard/response-safety-finance-binary-guardset-690b961164ad0e9988ed4703) | [0.8895](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-finance-binary-guardset) | [0.9303](https://huggingface.co/enguard/small-guard-32m-en-response-safety-finance-binary-guardset) | [0.9102](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-finance-binary-guardset) |
36
- | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | general-safety-social-media-binary | [Collection](https://huggingface.co/collections/enguard/general-safety-social-media-binary-guardset-690b960bd1b1444f6cb12fd8) | [0.9177](https://huggingface.co/enguard/tiny-guard-2m-en-general-safety-social-media-binary-guardset) | [0.9470](https://huggingface.co/enguard/tiny-guard-8m-en-general-safety-social-media-binary-guardset) | [0.9572](https://huggingface.co/enguard/medium-guard-128m-xx-general-safety-social-media-binary-guardset) |
37
- | [harmfulness-mix](https://huggingface.co/datasets/nicholasKluge/harmful-text) | prompt-harmfulness-binary | [Collection](https://huggingface.co/collections/enguard/prompt-harmfulness-binary-mix-6906407cc402663e1c636bd2) | [0.9177](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-harmfulness-binary-mix) | [0.9404](https://huggingface.co/enguard/small-guard-32m-en-prompt-harmfulness-binary-mix) | [0.9302](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-harmfulness-binary-mix) |
38
- | [in-the-wild](https://huggingface.co/datasets/TrustAIRLab/in-the-wild-jailbreak-prompts) | prompt-jailbreak-binary | [Collection](https://huggingface.co/collections/enguard/prompt-jailbreak-binary-in-the-wild-690640a36f0884de5cee00f1) | [0.8610](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-jailbreak-binary-in-the-wild) | [0.8610](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-jailbreak-binary-in-the-wild) | [0.8876](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-jailbreak-binary-in-the-wild) |
39
- | [intel](https://huggingface.co/datasets/Intel/polite-guard) | general-politeness-binary | [Collection](https://huggingface.co/collections/enguard/general-politeness-binary-intel-690640f133ad6c2f6a386f35) | [0.9933](https://huggingface.co/enguard/tiny-guard-2m-en-general-politeness-binary-intel) | [0.9937](https://huggingface.co/enguard/small-guard-32m-en-general-politeness-binary-intel) | [0.9934](https://huggingface.co/enguard/medium-guard-128m-xx-general-politeness-binary-intel) |
40
- | [intel](https://huggingface.co/datasets/Intel/polite-guard) | general-politeness-multiclass | [Collection](https://huggingface.co/collections/enguard/general-politeness-multiclass-intel-690aea7c4c4be3797665ac85) | [0.8814](https://huggingface.co/enguard/tiny-guard-2m-en-general-politeness-multiclass-intel) | [0.8974](https://huggingface.co/enguard/medium-guard-128m-xx-general-politeness-multiclass-intel) | [0.8974](https://huggingface.co/enguard/medium-guard-128m-xx-general-politeness-multiclass-intel) |
41
- | [jigsaw](https://huggingface.co/datasets/google/jigsaw_toxicity_pred) | prompt-toxicity-binary | [Collection](https://huggingface.co/collections/enguard/prompt-toxicity-binary-jigsaw-6906416fc6dee95ffbf95abc) | [0.8785](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-toxicity-binary-jigsaw) | [0.8785](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-toxicity-binary-jigsaw) | [0.8885](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-toxicity-binary-jigsaw) |
42
- | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-hate-speech-binary | [Collection](https://huggingface.co/collections/enguard/prompt-hate-speech-binary-moderation-690aeb975d13035cef706339) | [0.8440](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-hate-speech-binary-moderation) | [0.8868](https://huggingface.co/enguard/small-guard-32m-en-prompt-hate-speech-binary-moderation) | [0.8557](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-hate-speech-binary-moderation) |
43
- | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-harmfulness-binary | [Collection](https://huggingface.co/collections/enguard/prompt-harmfulness-binary-moderation-690aeb966312b2e4890f92ce) | [0.8075](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-harmfulness-binary-moderation) | [0.8345](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-harmfulness-binary-moderation) | [0.8302](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-harmfulness-binary-moderation) |
44
- | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-sexual-content-binary | [Collection](https://huggingface.co/collections/enguard/prompt-sexual-content-binary-moderation-690aeb994c4be3797665be72) | [0.8802](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-sexual-content-binary-moderation) | [0.9163](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-sexual-content-binary-moderation) | [0.8979](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-sexual-content-binary-moderation) |
45
- | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-harassment-binary | [Collection](https://huggingface.co/collections/enguard/prompt-harassment-binary-moderation-690aeb965d13035cef706323) | [0.8198](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-harassment-binary-moderation) | [0.8256](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-harassment-binary-moderation) | [0.8409](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-harassment-binary-moderation) |
46
- | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-self-harm-binary | [Collection](https://huggingface.co/collections/enguard/prompt-self-harm-binary-moderation-690aeb9888388f50cc54756c) | [0.8274](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-self-harm-binary-moderation) | [0.9083](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-self-harm-binary-moderation) | [0.9030](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-self-harm-binary-moderation) |
47
- | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-violence-binary | [Collection](https://huggingface.co/collections/enguard/prompt-violence-binary-moderation-690aeb9cfa6397707c0d021b) | [0.8487](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-violence-binary-moderation) | [0.9005](https://huggingface.co/enguard/small-guard-32m-en-prompt-violence-binary-moderation) | [0.8649](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-violence-binary-moderation) |
48
- | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-harmfulness-multilabel | [Collection](https://huggingface.co/collections/enguard/prompt-harmfulness-multilabel-moderation-690b9d20682fe55899d51d57) | [0.8055](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-harmfulness-multilabel-moderation) | [0.8160](https://huggingface.co/enguard/small-guard-32m-en-prompt-harmfulness-multilabel-moderation) | [0.7867](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-harmfulness-multilabel-moderation) |
49
- | [nvidia-aegis](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0) | prompt-response-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-response-safety-binary-nvidia-aegis-690aed7254d475b7a2def8a9) | [0.7851](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-response-safety-binary-nvidia-aegis) | [0.8126](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-response-safety-binary-nvidia-aegis) | [0.7717](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-response-safety-binary-nvidia-aegis) |
50
- | [nvidia-aegis](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0) | prompt-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-binary-nvidia-aegis-690641b0c402663e1c63918f) | [0.7753](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-binary-nvidia-aegis) | [0.8051](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-safety-binary-nvidia-aegis) | [0.8079](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-binary-nvidia-aegis) |
51
- | [nvidia-aegis](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0) | response-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-response-safety-binary-nvidia-aegis-690aed7254d475b7a2def8a9) | [0.7662](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-binary-nvidia-aegis) | [0.7928](https://huggingface.co/enguard/tiny-guard-4m-en-response-safety-binary-nvidia-aegis) | [0.7308](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-binary-nvidia-aegis) |
52
- | [polyguard](https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix) | prompt-safety-multilabel | [Collection](https://huggingface.co/collections/enguard/prompt-safety-multilabel-polyguard-69064247840509f3fc6fde9f) | [0.8341](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-multilabel-polyguard) | [0.8769](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-multilabel-polyguard) | [0.8769](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-multilabel-polyguard) |
53
- | [polyguard](https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix) | response-refusal-binary | [Collection](https://huggingface.co/collections/enguard/response-refusal-binary-polyguard-690642488736dfdcc6d7dadd) | [0.8974](https://huggingface.co/enguard/tiny-guard-2m-en-response-refusal-binary-polyguard) | [0.9115](https://huggingface.co/enguard/small-guard-32m-en-response-refusal-binary-polyguard) | [0.9094](https://huggingface.co/enguard/medium-guard-128m-xx-response-refusal-binary-polyguard) |
54
- | [polyguard](https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix) | prompt-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-binary-polyguard-6906424764ecfc28bdab268d) | [0.9190](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-binary-polyguard) | [0.9273](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-safety-binary-polyguard) | [0.9406](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-binary-polyguard) |
55
- | [polyguard](https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix) | response-safety-binary | [Collection](https://huggingface.co/collections/enguard/response-safety-binary-polyguard-6906424864be3f0c18024855) | [0.8637](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-binary-polyguard) | [0.8637](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-binary-polyguard) | [0.8738](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-binary-polyguard) |
56
- | [sok](https://huggingface.co/datasets/youbin2014/JailbreakDB) | prompt-jailbreak-binary | [Collection](https://huggingface.co/collections/enguard/prompt-jailbreak-binary-sok-6906471564be3f0c1802d8b8) | [0.9736](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-jailbreak-binary-sok) | [0.9816](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-jailbreak-binary-sok) | [0.9816](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-jailbreak-binary-sok) |
57
- | [toxic-chat](https://huggingface.co/datasets/lmsys/toxic-chat) | prompt-toxicity | [Collection](https://huggingface.co/collections/enguard/prompt-toxicity-toxic-chat-6906474e7b1bc88b334a092a) | [0.9511](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-toxicity-toxic-chat) | [0.9588](https://huggingface.co/enguard/small-guard-32m-en-prompt-toxicity-toxic-chat) | [0.9547](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-toxicity-toxic-chat) |
 
22
 
23
  | Dataset | Classifies | Collection | Smallest (2m) | Best Performing | Multi-lingual (128m) |
24
  | --- | --- | --- | --- | --- | --- |
25
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | general-safety-education-binary | [Collection](https://huggingface.co/collections/enguard/general-safety-education-binary-guardset-690b96092286c0e2c3b8a238) | [0.9672](https://huggingface.co/enguard/tiny-guard-2m-en-general-safety-education-binary-guardset) | [0.9835](https://huggingface.co/enguard/small-guard-32m-en-general-safety-education-binary-guardset) | [0.9806](https://huggingface.co/enguard/medium-guard-128m-xx-general-safety-education-binary-guardset) |
26
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | response-safety-cyber-binary | [Collection](https://huggingface.co/collections/enguard/response-safety-cyber-binary-guardset-690b9610479d2f239f958756) | [0.9623](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-cyber-binary-guardset) | [0.9681](https://huggingface.co/enguard/small-guard-32m-en-response-safety-cyber-binary-guardset) | [0.9607](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-cyber-binary-guardset) |
27
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-response-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-response-safety-binary-guardset-690b960c0326245fed30b069) | [0.9514](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-response-safety-binary-guardset) | [0.9783](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-response-safety-binary-guardset) | [0.9595](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-response-safety-binary-guardset) |
28
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-safety-finance-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-finance-binary-guardset-690b960ea52bbafc766f3058) | [0.9939](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-finance-binary-guardset) | [1.0000](https://huggingface.co/enguard/small-guard-32m-en-prompt-safety-finance-binary-guardset) | [1.0000](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-finance-binary-guardset) |
29
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | general-safety-hr-binary | [Collection](https://huggingface.co/collections/enguard/general-safety-hr-binary-guardset-690b960aa52bbafc766f2fff) | [0.9643](https://huggingface.co/enguard/tiny-guard-2m-en-general-safety-hr-binary-guardset) | [0.9868](https://huggingface.co/enguard/small-guard-32m-en-general-safety-hr-binary-guardset) | [0.9865](https://huggingface.co/enguard/medium-guard-128m-xx-general-safety-hr-binary-guardset) |
30
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-safety-law-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-law-binary-guardset-690b960f682fe55899d4ac74) | [0.9783](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-law-binary-guardset) | [1.0000](https://huggingface.co/enguard/small-guard-32m-en-prompt-safety-law-binary-guardset) | [0.9890](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-law-binary-guardset) |
31
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-binary-guardset-690b960d682fe55899d4ac45) | [0.9564](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-binary-guardset) | [0.9731](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-safety-binary-guardset) | [0.9676](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-binary-guardset) |
32
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | response-safety-law-binary | [Collection](https://huggingface.co/collections/enguard/response-safety-law-binary-guardset-690b9612682fe55899d4acae) | [0.9344](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-law-binary-guardset) | [0.9344](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-law-binary-guardset) | [0.9194](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-law-binary-guardset) |
33
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | response-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-response-safety-binary-guardset-690b960c0326245fed30b069) | [0.9338](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-binary-guardset) | [0.9484](https://huggingface.co/enguard/small-guard-32m-en-response-safety-binary-guardset) | [0.9279](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-binary-guardset) |
34
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | prompt-safety-cyber-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-cyber-binary-guardset-690b960d0326245fed30b089) | [0.9540](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-cyber-binary-guardset) | [0.9649](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-safety-cyber-binary-guardset) | [0.9558](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-cyber-binary-guardset) |
35
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | response-safety-finance-binary | [Collection](https://huggingface.co/collections/enguard/response-safety-finance-binary-guardset-690b961164ad0e9988ed4703) | [0.9350](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-finance-binary-guardset) | [0.9650](https://huggingface.co/enguard/small-guard-32m-en-response-safety-finance-binary-guardset) | [0.9381](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-finance-binary-guardset) |
36
+ | [guardset](https://huggingface.co/datasets/AI-Secure/PolyGuard) | general-safety-social-media-binary | [Collection](https://huggingface.co/collections/enguard/general-safety-social-media-binary-guardset-690b960bd1b1444f6cb12fd8) | [0.9484](https://huggingface.co/enguard/tiny-guard-2m-en-general-safety-social-media-binary-guardset) | [0.9793](https://huggingface.co/enguard/tiny-guard-8m-en-general-safety-social-media-binary-guardset) | [0.9690](https://huggingface.co/enguard/medium-guard-128m-xx-general-safety-social-media-binary-guardset) |
37
+ | [harmfulness-mix](https://huggingface.co/datasets/nicholasKluge/harmful-text) | prompt-harmfulness-binary | [Collection](https://huggingface.co/collections/enguard/prompt-harmfulness-binary-mix-6906407cc402663e1c636bd2) | [0.9533](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-harmfulness-binary-mix) | [0.9579](https://huggingface.co/enguard/small-guard-32m-en-prompt-harmfulness-binary-mix) | [0.9558](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-harmfulness-binary-mix) |
38
+ | [in-the-wild](https://huggingface.co/datasets/TrustAIRLab/in-the-wild-jailbreak-prompts) | prompt-jailbreak-binary | [Collection](https://huggingface.co/collections/enguard/prompt-jailbreak-binary-in-the-wild-690640a36f0884de5cee00f1) | [0.9535](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-jailbreak-binary-in-the-wild) | [0.9535](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-jailbreak-binary-in-the-wild) | [0.9240](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-jailbreak-binary-in-the-wild) |
39
+ | [intel](https://huggingface.co/datasets/Intel/polite-guard) | general-politeness-binary | [Collection](https://huggingface.co/collections/enguard/general-politeness-binary-intel-690640f133ad6c2f6a386f35) | [0.9843](https://huggingface.co/enguard/tiny-guard-2m-en-general-politeness-binary-intel) | [0.9858](https://huggingface.co/enguard/small-guard-32m-en-general-politeness-binary-intel) | [0.9831](https://huggingface.co/enguard/medium-guard-128m-xx-general-politeness-binary-intel) |
40
+ | [intel](https://huggingface.co/datasets/Intel/polite-guard) | general-politeness-multiclass | [Collection](https://huggingface.co/collections/enguard/general-politeness-multiclass-intel-690aea7c4c4be3797665ac85) | [0.9951](https://huggingface.co/enguard/tiny-guard-2m-en-general-politeness-multiclass-intel) | [0.9992](https://huggingface.co/enguard/medium-guard-128m-xx-general-politeness-multiclass-intel) | [0.9992](https://huggingface.co/enguard/medium-guard-128m-xx-general-politeness-multiclass-intel) |
41
+ | [jigsaw](https://huggingface.co/datasets/google/jigsaw_toxicity_pred) | prompt-toxicity-binary | [Collection](https://huggingface.co/collections/enguard/prompt-toxicity-binary-jigsaw-6906416fc6dee95ffbf95abc) | [0.9531](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-toxicity-binary-jigsaw) | [0.9531](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-toxicity-binary-jigsaw) | [0.9111](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-toxicity-binary-jigsaw) |
42
+ | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-hate-speech-binary | [Collection](https://huggingface.co/collections/enguard/prompt-hate-speech-binary-moderation-690aeb975d13035cef706339) | [0.9141](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-hate-speech-binary-moderation) | [0.9207](https://huggingface.co/enguard/small-guard-32m-en-prompt-hate-speech-binary-moderation) | [0.8826](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-hate-speech-binary-moderation) |
43
+ | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-harmfulness-binary | [Collection](https://huggingface.co/collections/enguard/prompt-harmfulness-binary-moderation-690aeb966312b2e4890f92ce) | [0.8543](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-harmfulness-binary-moderation) | [0.8627](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-harmfulness-binary-moderation) | [0.8457](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-harmfulness-binary-moderation) |
44
+ | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-sexual-content-binary | [Collection](https://huggingface.co/collections/enguard/prompt-sexual-content-binary-moderation-690aeb994c4be3797665be72) | [0.9256](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-sexual-content-binary-moderation) | [0.9382](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-sexual-content-binary-moderation) | [0.9153](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-sexual-content-binary-moderation) |
45
+ | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-harassment-binary | [Collection](https://huggingface.co/collections/enguard/prompt-harassment-binary-moderation-690aeb965d13035cef706323) | [0.8788](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-harassment-binary-moderation) | [0.8895](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-harassment-binary-moderation) | [0.8660](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-harassment-binary-moderation) |
46
+ | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-self-harm-binary | [Collection](https://huggingface.co/collections/enguard/prompt-self-harm-binary-moderation-690aeb9888388f50cc54756c) | [0.8929](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-self-harm-binary-moderation) | [0.9667](https://huggingface.co/enguard/tiny-guard-8m-en-prompt-self-harm-binary-moderation) | [0.9375](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-self-harm-binary-moderation) |
47
+ | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-violence-binary | [Collection](https://huggingface.co/collections/enguard/prompt-violence-binary-moderation-690aeb9cfa6397707c0d021b) | [0.9017](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-violence-binary-moderation) | [0.9077](https://huggingface.co/enguard/small-guard-32m-en-prompt-violence-binary-moderation) | [0.8821](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-violence-binary-moderation) |
48
+ | [moderation](https://huggingface.co/datasets/enguard/multi-lingual-prompt-moderation) | prompt-harmfulness-multilabel | [Collection](https://huggingface.co/collections/enguard/prompt-harmfulness-multilabel-moderation-690b9d20682fe55899d51d57) | [0.6185](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-harmfulness-multilabel-moderation) | [0.6909](https://huggingface.co/enguard/small-guard-32m-en-prompt-harmfulness-multilabel-moderation) | [0.6547](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-harmfulness-multilabel-moderation) |
49
+ | [nvidia-aegis](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0) | prompt-response-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-response-safety-binary-nvidia-aegis-690aed7254d475b7a2def8a9) | [0.8254](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-response-safety-binary-nvidia-aegis) | [0.8300](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-response-safety-binary-nvidia-aegis) | [0.7878](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-response-safety-binary-nvidia-aegis) |
50
+ | [nvidia-aegis](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0) | prompt-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-binary-nvidia-aegis-690641b0c402663e1c63918f) | [0.8770](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-binary-nvidia-aegis) | [0.8945](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-safety-binary-nvidia-aegis) | [0.8688](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-binary-nvidia-aegis) |
51
+ | [nvidia-aegis](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0) | response-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-response-safety-binary-nvidia-aegis-690aed7254d475b7a2def8a9) | [0.8631](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-binary-nvidia-aegis) | [0.8736](https://huggingface.co/enguard/tiny-guard-4m-en-response-safety-binary-nvidia-aegis) | [0.7560](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-binary-nvidia-aegis) |
52
+ | [polyguard](https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix) | prompt-safety-multilabel | [Collection](https://huggingface.co/collections/enguard/prompt-safety-multilabel-polyguard-69064247840509f3fc6fde9f) | [0.6619](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-multilabel-polyguard) | [0.7955](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-multilabel-polyguard) | [0.7955](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-multilabel-polyguard) |
53
+ | [polyguard](https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix) | response-refusal-binary | [Collection](https://huggingface.co/collections/enguard/response-refusal-binary-polyguard-690642488736dfdcc6d7dadd) | [0.9486](https://huggingface.co/enguard/tiny-guard-2m-en-response-refusal-binary-polyguard) | [0.9567](https://huggingface.co/enguard/small-guard-32m-en-response-refusal-binary-polyguard) | [0.9510](https://huggingface.co/enguard/medium-guard-128m-xx-response-refusal-binary-polyguard) |
54
+ | [polyguard](https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix) | prompt-safety-binary | [Collection](https://huggingface.co/collections/enguard/prompt-safety-binary-polyguard-6906424764ecfc28bdab268d) | [0.9740](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-binary-polyguard) | [0.9741](https://huggingface.co/enguard/tiny-guard-4m-en-prompt-safety-binary-polyguard) | [0.9609](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-safety-binary-polyguard) |
55
+ | [polyguard](https://huggingface.co/datasets/ToxicityPrompts/PolyGuardMix) | response-safety-binary | [Collection](https://huggingface.co/collections/enguard/response-safety-binary-polyguard-6906424864be3f0c18024855) | [0.9535](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-binary-polyguard) | [0.9535](https://huggingface.co/enguard/tiny-guard-2m-en-response-safety-binary-polyguard) | [0.9447](https://huggingface.co/enguard/medium-guard-128m-xx-response-safety-binary-polyguard) |
56
+ | [sok](https://huggingface.co/datasets/youbin2014/JailbreakDB) | prompt-jailbreak-binary | [Collection](https://huggingface.co/collections/enguard/prompt-jailbreak-binary-sok-6906471564be3f0c1802d8b8) | [0.9862](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-jailbreak-binary-sok) | [0.9901](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-jailbreak-binary-sok) | [0.9901](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-jailbreak-binary-sok) |
57
+ | [toxic-chat](https://huggingface.co/datasets/lmsys/toxic-chat) | prompt-toxicity | [Collection](https://huggingface.co/collections/enguard/prompt-toxicity-toxic-chat-6906474e7b1bc88b334a092a) | [0.5820](https://huggingface.co/enguard/tiny-guard-2m-en-prompt-toxicity-toxic-chat) | [0.6852](https://huggingface.co/enguard/small-guard-32m-en-prompt-toxicity-toxic-chat) | [0.6129](https://huggingface.co/enguard/medium-guard-128m-xx-prompt-toxicity-toxic-chat) |