Hugging Face's logo

madbit
/
LaBSE-ru-turbo-inference

Sentence Similarity
sentence-transformers
Safetensors
Transformers
Russian
bert
feature-extraction
russian
pretraining
embeddings
text-embeddings-inference
Model card Files
xet
Community
madbit commited on
Commit
40f01bc
·
verified ·
1 Parent(s): 9755bea

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +7 -0
  2. README.md +97 -0
  3. config.json +32 -0
  4. config_sentence_transformers.json +11 -0
  5. model.safetensors +3 -0
  6. modules.json +20 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +37 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +58 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false
7
+ }
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ru
4
+
5
+ pipeline_tag: sentence-similarity
6
+
7
+ tags:
8
+ - russian
9
+ - pretraining
10
+ - embeddings
11
+ - feature-extraction
12
+ - sentence-similarity
13
+ - sentence-transformers
14
+ - transformers
15
+
16
+ datasets:
17
+ - IlyaGusev/gazeta
18
+ - zloelias/lenta-ru
19
+
20
+ license: mit
21
+ base_model: cointegrated/LaBSE-en-ru
22
+
23
+ ---
24
+
25
+ Модель BERT для расчетов эмбеддингов предложений на русском языке. Модель основана на [cointegrated/LaBSE-en-ru](https://huggingface.co/cointegrated/LaBSE-en-ru) - имеет аналогичные размеры контекста (512), ембеддинга (768) и быстродействие.
26
+
27
+
28
+ ## Использование:
29
+ ```Python
30
+ from sentence_transformers import SentenceTransformer, util
31
+
32
+ model = SentenceTransformer('sergeyzh/LaBSE-ru-turbo')
33
+
34
+ sentences = ["привет мир", "hello world", "здравствуй вселенная"]
35
+ embeddings = model.encode(sentences)
36
+ print(util.dot_score(embeddings, embeddings))
37
+ ```
38
+
39
+ ## Метрики
40
+ Оценки модели на бенчмарке [encodechka](https://github.com/sergeyz-zh/encodechka):
41
+
42
+ | Model | CPU | GPU | size | Mean S | Mean S+W | dim |
43
+ |:-----------------------------------|----------:|---------:|---------:|----------:|-----------:|-------:|
44
+ | **sergeyzh/LaBSE-ru-turbo** | 120.40 | 8.05 | 490 | 0.789 | 0.702 | 768 |
45
+ | BAAI/bge-m3 | 523.40 | 22.50 | 2166 | 0.787 | 0.696 | 1024 |
46
+ | intfloat/multilingual-e5-large | 506.80 | 30.80 | 2136 | 0.780 | 0.686 | 1024 |
47
+ | intfloat/multilingual-e5-base | 130.61 | 14.39 | 1061 | 0.761 | 0.669 | 768 |
48
+ | [sergeyzh/rubert-tiny-turbo](https://huggingface.co/sergeyzh/rubert-tiny-turbo) | 5.51 | 3.25 | 111 | 0.749 | 0.667 | 312 |
49
+ | intfloat/multilingual-e5-small | 40.86 | 12.09 | 449 | 0.742 | 0.645 | 384 |
50
+ | cointegrated/LaBSE-en-ru | 120.40 | 8.05 | 490 | 0.739 | 0.667 | 768 |
51
+
52
+ | Model | STS | PI | NLI | SA | TI | IA | IC | ICX | NE1 | NE2 |
53
+ |:-----------------------------------|:---------|:---------|:---------|:---------|:---------|:---------|:---------|:---------|:---------|:---------|
54
+ | **sergeyzh/LaBSE-ru-turbo** | 0.864 | 0.748 | 0.490 | 0.814 | 0.974 | 0.806 | 0.815 | 0.801 | 0.305 | 0.404 |
55
+ | BAAI/bge-m3 | 0.864 | 0.749 | 0.510 | 0.819 | 0.973 | 0.792 | 0.809 | 0.783 | 0.240 | 0.422 |
56
+ | intfloat/multilingual-e5-large | 0.862 | 0.727 | 0.473 | 0.810 | 0.979 | 0.798 | 0.819 | 0.773 | 0.224 | 0.374 |
57
+ | intfloat/multilingual-e5-base | 0.835 | 0.704 | 0.459 | 0.796 | 0.964 | 0.783 | 0.802 | 0.738 | 0.235 | 0.376 |
58
+ | [sergeyzh/rubert-tiny-turbo](https://huggingface.co/sergeyzh/rubert-tiny-turbo) | 0.828 | 0.722 | 0.476 | 0.787 | 0.955 | 0.757 | 0.780 | 0.685 | 0.305 | 0.373 |
59
+ | intfloat/multilingual-e5-small | 0.822 | 0.714 | 0.457 | 0.758 | 0.957 | 0.761 | 0.779 | 0.691 | 0.234 | 0.275 |
60
+ | cointegrated/LaBSE-en-ru | 0.794 | 0.659 | 0.431 | 0.761 | 0.946 | 0.766 | 0.789 | 0.769 | 0.340 | 0.414 |
61
+
62
+
63
+ Оценки модели на бенчмарке [ruMTEB](https://habr.com/ru/companies/sberdevices/articles/831150/):
64
+
65
+ |Model Name | Metric | sbert_large_ mt_nlu_ru | sbert_large_ nlu_ru | [LaBSE-ru-sts](https://huggingface.co/sergeyzh/LaBSE-ru-sts) | LaBSE-ru-turbo | multilingual-e5-small | multilingual-e5-base | multilingual-e5-large |
66
+ |:----------------------------------|:--------------------|-----------------------:|--------------------:|----------------:|------------------:|----------------------:|---------------------:|----------------------:|
67
+ |CEDRClassification | Accuracy | 0.368 | 0.358 | 0.418 | 0.451 | 0.401 | 0.423 | **0.448** |
68
+ |GeoreviewClassification | Accuracy | 0.397 | 0.400 | 0.406 | 0.438 | 0.447 | 0.461 | **0.497** |
69
+ |GeoreviewClusteringP2P | V-measure | 0.584 | 0.590 | 0.626 | **0.644** | 0.586 | 0.545 | 0.605 |
70
+ |HeadlineClassification | Accuracy | 0.772 | **0.793** | 0.633 | 0.688 | 0.732 | 0.757 | 0.758 |
71
+ |InappropriatenessClassification | Accuracy | **0.646** | 0.625 | 0.599 | 0.615 | 0.592 | 0.588 | 0.616 |
72
+ |KinopoiskClassification | Accuracy | 0.503 | 0.495 | 0.496 | 0.521 | 0.500 | 0.509 | **0.566** |
73
+ |RiaNewsRetrieval | NDCG@10 | 0.214 | 0.111 | 0.651 | 0.694 | 0.700 | 0.702 | **0.807** |
74
+ |RuBQReranking | MAP@10 | 0.561 | 0.468 | 0.688 | 0.687 | 0.715 | 0.720 | **0.756** |
75
+ |RuBQRetrieval | NDCG@10 | 0.298 | 0.124 | 0.622 | 0.657 | 0.685 | 0.696 | **0.741** |
76
+ |RuReviewsClassification | Accuracy | 0.589 | 0.583 | 0.599 | 0.632 | 0.612 | 0.630 | **0.653** |
77
+ |RuSTSBenchmarkSTS | Pearson correlation | 0.712 | 0.588 | 0.788 | 0.822 | 0.781 | 0.796 | **0.831** |
78
+ |RuSciBenchGRNTIClassification | Accuracy | 0.542 | 0.539 | 0.529 | 0.569 | 0.550 | 0.563 | **0.582** |
79
+ |RuSciBenchGRNTIClusteringP2P | V-measure | **0.522** | 0.504 | 0.486 | 0.517 | 0.511 | 0.516 | 0.520 |
80
+ |RuSciBenchOECDClassification | Accuracy | 0.438 | 0.430 | 0.406 | 0.440 | 0.427 | 0.423 | **0.445** |
81
+ |RuSciBenchOECDClusteringP2P | V-measure | **0.473** | 0.464 | 0.426 | 0.452 | 0.443 | 0.448 | 0.450 |
82
+ |SensitiveTopicsClassification | Accuracy | **0.285** | 0.280 | 0.262 | 0.272 | 0.228 | 0.234 | 0.257 |
83
+ |TERRaClassification | Average Precision | 0.520 | 0.502 | **0.587** | 0.585 | 0.551 | 0.550 | 0.584 |
84
+
85
+ |Model Name | Metric | sbert_large_ mt_nlu_ru | sbert_large_ nlu_ru | [LaBSE-ru-sts](https://huggingface.co/sergeyzh/LaBSE-ru-sts) | LaBSE-ru-turbo | multilingual-e5-small | multilingual-e5-base | multilingual-e5-large |
86
+ |:----------------------------------|:--------------------|-----------------------:|--------------------:|----------------:|------------------:|----------------------:|----------------------:|---------------------:|
87
+ |Classification | Accuracy | 0.554 | 0.552 | 0.524 | 0.558 | 0.551 | 0.561 | **0.588** |
88
+ |Clustering | V-measure | 0.526 | 0.519 | 0.513 | **0.538** | 0.513 | 0.503 | 0.525 |
89
+ |MultiLabelClassification | Accuracy | 0.326 | 0.319 | 0.340 | **0.361** | 0.314 | 0.329 | 0.353 |
90
+ |PairClassification | Average Precision | 0.520 | 0.502 | 0.587 | **0.585** | 0.551 | 0.550 | 0.584 |
91
+ |Reranking | MAP@10 | 0.561 | 0.468 | 0.688 | 0.687 | 0.715 | 0.720 | **0.756** |
92
+ |Retrieval | NDCG@10 | 0.256 | 0.118 | 0.637 | 0.675 | 0.697 | 0.699 | **0.774** |
93
+ |STS | Pearson correlation | 0.712 | 0.588 | 0.788 | 0.822 | 0.781 | 0.796 | **0.831** |
94
+ |Average | Average | 0.494 | 0.438 | 0.582 | 0.604 | 0.588 | 0.594 | **0.630** |
95
+
96
+
97
+
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sergeyzh/LaBSE-ru-turbo",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 0,
21
+ "pooler_fc_size": 768,
22
+ "pooler_num_attention_heads": 12,
23
+ "pooler_num_fc_layers": 3,
24
+ "pooler_size_per_head": 128,
25
+ "pooler_type": "first_token_transform",
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.38.1",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 55083
32
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SentenceTransformer"
4
+ ],
5
+ "framework": "pt",
6
+ "pooling_mode_cls_token": false,
7
+ "pooling_mode_mean_tokens": true,
8
+ "pooling_mode_max_tokens": false,
9
+ "pooling_mode_lasttoken": false,
10
+ "whitening": false
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b792d46c3c478a746e20ea9f982a45c17ca03f7fd08c4a3f174b167de97396
3
+ size 134
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff