First commit

README.md

@@ -0,0 +1,38 @@
+---
+language:
+- en
+license: apache-2.0
+datasets:
+- Open-Orca/OpenOrca
+- jackhhao/jailbreak-classification
+metrics:
+- accuracy
+library_name: transformers
+pipeline_tag: text-classification
+tags:
+- jailbreak
+- security
+- moderation
+- prompt-injection
+---
+
+# Jailbreak Classifier
+
+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.
+
+## Training Details
+
+### Training Data
+
+Fine-tuned on the [jailbreak-classification](https://huggingface.co/datasets/jackhhao/jailbreak-classification) dataset.
+
+### Training Procedure 
+
+#### Training Hyperparameters
+
+Fine-tuning hyper-parameters:
+- learning_rate = 5e-5
+- train_batch_size = 8
+- eval_batch_size = 8
+- lr_scheduler_type = linear
+- num_train_epochs = 5.0

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "../model",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "benign",
+    "1": "jailbreak"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "benign": 0,
+    "jailbreak": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:450171758333f23800a7283e74f638d11f38a5b56420445ee2d0d2a6e35ee37e
+size 438001134

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}