Hugging Face's logo

Serhii228
/
ukrainian-question-statement-classifier

Text Classification
TensorFlow
Ukrainian
xlm-roberta
roberta
ukraine
binary-classification
question-detection
Model card Files Community
Serhii228 commited on
Commit
eb43cc2
·
verified ·
1 Parent(s): cbe305e

Upload 6 files

Browse files
Files changed (5) hide show
  1. config.json +32 -33
  2. special_tokens_map.json +51 -15
  3. tf_model.h5 +1 -1
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +55 -54
config.json CHANGED
@@ -1,33 +1,32 @@
1
- {
2
- "_name_or_path": "xlm-roberta-base",
3
- "architectures": [
4
- "XLMRobertaForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": null,
9
- "eos_token_id": 2,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 768,
13
- "id2label": {
14
- "0": "LABEL_0"
15
- },
16
- "initializer_range": 0.02,
17
- "intermediate_size": 3072,
18
- "label2id": {
19
- "LABEL_0": 0
20
- },
21
- "layer_norm_eps": 1e-05,
22
- "max_position_embeddings": 514,
23
- "model_type": "xlm-roberta",
24
- "num_attention_heads": 12,
25
- "num_hidden_layers": 12,
26
- "output_past": true,
27
- "pad_token_id": 1,
28
- "position_embedding_type": "absolute",
29
- "transformers_version": "4.39.3",
30
- "type_vocab_size": 1,
31
- "use_cache": true,
32
- "vocab_size": 250002
33
- }
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-05,
21
+ "max_position_embeddings": 514,
22
+ "model_type": "xlm-roberta",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "absolute",
28
+ "transformers_version": "4.51.0",
29
+ "type_vocab_size": 1,
30
+ "use_cache": true,
31
+ "vocab_size": 250002
32
+ }
 
special_tokens_map.json CHANGED
@@ -1,15 +1,51 @@
1
- {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29e6e45ab2440074dba01c1f0f81fc18ff47342537132eb63003f94888764fbd
3
  size 1112467264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f502513fbfbdb1654bc2534bdc06315c170d1c08d5951f86c0ff9c09f288b83e
3
  size 1112467264
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
3
- size 17082756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a514807cffabd8abaf028cfaffe7ff0c4f60b97ea2db80c41f14172ae6b018ca
3
+ size 17082987
tokenizer_config.json CHANGED
@@ -1,54 +1,55 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<pad>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "<unk>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "250001": {
36
- "content": "<mask>",
37
- "lstrip": true,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
- "mask_token": "<mask>",
49
- "model_max_length": 512,
50
- "pad_token": "<pad>",
51
- "sep_token": "</s>",
52
- "tokenizer_class": "XLMRobertaTokenizer",
53
- "unk_token": "<unk>"
54
- }
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }