Hugging Face's logo

qwazer
/
rubert-address-elements

Token Classification
Transformers
TensorBoard
Safetensors
Russian
bert
address
Inference Endpoints
Model card Files Metrics Community
qwazer commited on
Commit
e9ade1e
•
1 Parent(s): 73757ef

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +55 -0
  2. model.safetensors +3 -0
  3. runs/May20_07-41-38_8384c2a257c5/events.out.tfevents.1716190904.8384c2a257c5.1528.0 +3 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +64 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "OTHER",
15
+ "1": "REGION",
16
+ "2": "REGION_TYPE",
17
+ "3": "AREA",
18
+ "4": "AREA_TYPE",
19
+ "5": "TERRITORY",
20
+ "6": "TERRITORY_TYPE",
21
+ "7": "CITY",
22
+ "8": "CITY_TYPE",
23
+ "9": "STREET",
24
+ "10": "STREET_TYPE",
25
+ "11": "DELIMITER"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 600,
29
+ "label2id": {
30
+ "AREA": 3,
31
+ "AREA_TYPE": 4,
32
+ "CITY": 7,
33
+ "CITY_TYPE": 8,
34
+ "DELIMITER": 11,
35
+ "OTHER": 0,
36
+ "REGION": 1,
37
+ "REGION_TYPE": 2,
38
+ "STREET": 9,
39
+ "STREET_TYPE": 10,
40
+ "TERRITORY": 5,
41
+ "TERRITORY_TYPE": 6
42
+ },
43
+ "layer_norm_eps": 1e-12,
44
+ "max_position_embeddings": 2048,
45
+ "model_type": "bert",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 3,
48
+ "pad_token_id": 0,
49
+ "position_embedding_type": "absolute",
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.40.2",
52
+ "type_vocab_size": 2,
53
+ "use_cache": true,
54
+ "vocab_size": 83828
55
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d0483e5f4a041646c36bddd88e2a95acea0b720f6cd571e9da7955180af30bc
3
+ size 116405840
runs/May20_07-41-38_8384c2a257c5/events.out.tfevents.1716190904.8384c2a257c5.1528.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33e00def7c5d3d45afa0eff412715b609307f4475cea23b34a72a16d7fe350f1
3
+ size 60588
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 2048,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f243e11b909d40555978b91e26e36429850e734e393d261609d625f8bcd8cbf0
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff