Ertugrul commited on
Commit
edca3ac
1 Parent(s): bdf3709

Upload ./ with huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stage_f/pretrain_mlm_distilbert-base-turkish-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "dim": 768,
10
+ "dropout": 0.1,
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "INSULT",
14
+ "1": "OTHER",
15
+ "2": "PROFANITY",
16
+ "3": "RACIST",
17
+ "4": "SEXIST"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "INSULT": 0,
22
+ "OTHER": 1,
23
+ "PROFANITY": 2,
24
+ "RACIST": 3,
25
+ "SEXIST": 4
26
+ },
27
+ "max_position_embeddings": 512,
28
+ "model_type": "distilbert",
29
+ "n_heads": 12,
30
+ "n_layers": 6,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "qa_dropout": 0.1,
35
+ "seq_classif_dropout": 0.2,
36
+ "sinusoidal_pos_embds": true,
37
+ "tie_weights_": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.24.0",
40
+ "vocab_size": 32000
41
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3204e18b1753ece44aeb633c5d64a3aeec2921824cd963732069eefd3c3cdc91
3
+ size 272405165
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_distilbert-base-turkish-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": "DistilBertTokenizer",
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:b27b21bf371fffc99976f1061bad1fadc64fac7df8181bd216ad79b9f6544f7e
3
+ size 3451
vocab.txt ADDED
The diff for this file is too large to render. See raw diff