Update README.md

README.md

@@ -3,6 +3,10 @@ library_name: transformers
 license: mit
 base_model: microsoft/mdeberta-v3-base
 tags:
+- prompt-injection
+- injection
+- security
+- llm-security
 - generated_from_trainer
 metrics:
 - accuracy
@@ -14,70 +18,24 @@ model-index:
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
 # mdeberta-v3-base-prompt-injection
 
-This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.2258
-- Accuracy: 0.9661
-- Precision: 0.9924
-- Recall: 0.9129
-- F1: 0.9510
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
+This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on a combination of [jackhhao/jailbreak-classification](https://huggingface.co/datasets/jackhhao/jailbreak-classification), [deepset/prompt-injections](https://huggingface.co/datasets/deepset/prompt-injections/viewer/default/test?views%5B%5D=test), a custom datasets containing known attacks, and injections nested in legitimate content like websites and articles.
 
-The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 9
-- eval_batch_size: 9
-- seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 9
+## Usage
 
-### Training results
+```Python
+from transformers import pipeline
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
-|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.4808        | 0.5556 | 200  | 0.2098          | 0.9435   | 0.9690    | 0.8711 | 0.9174 |
-| 0.2477        | 1.1111 | 400  | 0.2381          | 0.9423   | 0.9170    | 0.9233 | 0.9201 |
-| 0.1586        | 1.6667 | 600  | 0.2516          | 0.9511   | 0.9697    | 0.8920 | 0.9292 |
-| 0.1685        | 2.2222 | 800  | 0.2001          | 0.9561   | 0.9468    | 0.9303 | 0.9385 |
-| 0.1275        | 2.7778 | 1000 | 0.1993          | 0.9548   | 0.9772    | 0.8955 | 0.9345 |
-| 0.0755        | 3.3333 | 1200 | 0.2840          | 0.9473   | 0.9960    | 0.8571 | 0.9213 |
-| 0.0944        | 3.8889 | 1400 | 0.2488          | 0.9473   | 0.9960    | 0.8571 | 0.9213 |
-| 0.092         | 4.4444 | 1600 | 0.2071          | 0.9636   | 0.9886    | 0.9094 | 0.9474 |
-| 0.067         | 5.0    | 1800 | 0.2779          | 0.9586   | 0.9669    | 0.9164 | 0.9410 |
-| 0.0572        | 5.5556 | 2000 | 0.1707          | 0.9649   | 0.9924    | 0.9094 | 0.9491 |
-| 0.052         | 6.1111 | 2200 | 0.2173          | 0.9573   | 0.9961    | 0.8850 | 0.9373 |
-| 0.0487        | 6.6667 | 2400 | 0.1827          | 0.9699   | 0.9852    | 0.9303 | 0.9570 |
-| 0.038         | 7.2222 | 2600 | 0.1954          | 0.9686   | 0.9888    | 0.9233 | 0.9550 |
-| 0.0361        | 7.7778 | 2800 | 0.1816          | 0.9686   | 0.9816    | 0.9303 | 0.9553 |
-| 0.0417        | 8.3333 | 3000 | 0.2194          | 0.9661   | 0.9924    | 0.9129 | 0.9510 |
-| 0.0278        | 8.8889 | 3200 | 0.2258          | 0.9661   | 0.9924    | 0.9129 | 0.9510 |
+classifier = pipeline(
+  "text-classification",
+  model="proventra/mdeberta-v3-base-prompt-injection"
+)
 
+print(classifier("Your text to scan"))
+```
 
-### Framework versions
+## Use in Proventra Core
+[proventra-core](https://github.com/proventra/proventra-core) python library
 
-- Transformers 4.51.3
-- Pytorch 2.6.0+cu124
-- Datasets 3.5.0
-- Tokenizers 0.21.1
+check out [Proventra](https://www.proventra-ai.com)