Ertugrul commited on
Commit
241c19f
1 Parent(s): f68699e

Upload ./ with huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stage_f/pretrain_mlm_bert-base-turkish-128k-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "INSULT",
13
+ "1": "OTHER",
14
+ "2": "PROFANITY",
15
+ "3": "RACIST",
16
+ "4": "SEXIST"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "INSULT": 0,
22
+ "OTHER": 1,
23
+ "PROFANITY": 2,
24
+ "RACIST": 3,
25
+ "SEXIST": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.24.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 128000
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763b90eefdf51a6386b4bbc94f09f2c10b5cb18c79658d215cd69d001a7cf4ac
3
+ size 737469557
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "name_or_path": "stage_f/pretrain_mlm_bert-base-turkish-128k-cased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3619281e65536696cd7bb6a262fb0a9718e22dd92a16b2cf116d32d79caa1150
3
+ size 3451
vocab.txt ADDED
The diff for this file is too large to render. See raw diff