jackhhao commited on
Commit
771aa6f
1 Parent(s): dc01ec4

Minor model card edits

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -13,17 +13,18 @@ tags:
13
  - jailbreak
14
  - security
15
  - moderation
 
16
  ---
17
 
18
  # Jailbreak Classifier
19
 
20
- Classifies prompts as jailbreaks or benign. This is a fine-tune checkpoint of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the [jailbreak-classification](https://huggingface.co/datasets/jackhhao/jailbreak-classification) dataaset.
21
 
22
  ## Training Details
23
 
24
  ### Training Data
25
 
26
- Fine-tuned on the [jailbreak-classification](https://huggingface.co/datasets/jackhhao/jailbreak-classification) dataaset.
27
 
28
  ### Training Procedure
29
 
@@ -31,7 +32,7 @@ Fine-tuned on the [jailbreak-classification](https://huggingface.co/datasets/jac
31
 
32
  Fine-tuning hyper-parameters:
33
  - learning_rate = 5e-5
34
- - per_device_train_batch_size = 8
35
- - per_device_eval_batch_size = 8
36
  - lr_scheduler_type = linear
37
  - num_train_epochs = 5.0
 
13
  - jailbreak
14
  - security
15
  - moderation
16
+ - prompt-injection
17
  ---
18
 
19
  # Jailbreak Classifier
20
 
21
+ Classifies prompts as jailbreaks or benign. This is a fine-tune checkpoint of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the [jailbreak-classification](https://huggingface.co/datasets/jackhhao/jailbreak-classification) dataset.
22
 
23
  ## Training Details
24
 
25
  ### Training Data
26
 
27
+ Fine-tuned on the [jailbreak-classification](https://huggingface.co/datasets/jackhhao/jailbreak-classification) dataset.
28
 
29
  ### Training Procedure
30
 
 
32
 
33
  Fine-tuning hyper-parameters:
34
  - learning_rate = 5e-5
35
+ - train_batch_size = 8
36
+ - eval_batch_size = 8
37
  - lr_scheduler_type = linear
38
  - num_train_epochs = 5.0