Update promptguard_utils.py #122
Conversation
fix(promptguard): add detailed reason and score to jailbreak detection output - Extended `get_jailbreak_score` to return both probability score and textual reason. - Added safe extraction with default fallback values to avoid crashes if fields are missing. - Improved logging for preprocessing and scoring stages. This change ensures downstream consumers (e.g., Promptfoo or LlamaFirewall API) can directly access structured `reason` and `score` without requiring a separate transform step.
|
Hi @d1pakda5! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at [email protected]. Thanks! |
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks! |
1 participant
fix(promptguard): add safe device handling and stable model loading
_safe_move_to_deviceto gracefully handle NotImplementedErrorand unexpected errors during
model.to(device)_pick_deviceto prioritize MPS → CUDA → CPUdevice_map=None,low_cpu_mem_usage=False, andtorch_dtype=torch.float32to avoid meta-tensor crashes