Dotan Nahum commited on
Commit
c7d039d
1 Parent(s): f60423a
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ checkpoint-*/.DS_Store
2
+ .DS_Store
README.md ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - deepset/prompt-injections
5
+ language:
6
+ - en
7
+ - de
8
+ - es
9
+ metrics:
10
+ - accuracy
11
+ library_name: transformers
12
+ ---
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "id2label": {
8
+ "0": "LEGIT",
9
+ "1": "INJECTION"
10
+ },
11
+ "label2id": {
12
+ "INJECTION": 1,
13
+ "LEGIT": 0
14
+ },
15
+ "attention_dropout": 0.1,
16
+ "dim": 768,
17
+ "dropout": 0.1,
18
+ "hidden_dim": 3072,
19
+ "initializer_range": 0.02,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
25
+ "problem_type": "single_label_classification",
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "tie_weights_": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.30.2",
32
+ "vocab_size": 30522
33
+ }
rust_model.ot ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a22b455b2ed4874dce25111a830a938bfe5dc82886f3610adae868c3c3551e
3
+ size 267853459
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b27f52d41172a53c87ce5a886954781ad53dc50fe659aff6798112483e4c8a
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff