sergeyzh commited on
Commit
8ce0cf7
1 Parent(s): f029c00

Upload 10 files

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 312,
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 CHANGED
@@ -1,3 +1,64 @@
1
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  license: mit
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - ru
4
+
5
+ pipeline_tag: sentence-similarity
6
+
7
+ tags:
8
+ - russian
9
+ - pretraining
10
+ - embeddings
11
+ - tiny
12
+ - feature-extraction
13
+ - sentence-similarity
14
+ - sentence-transformers
15
+ - transformers
16
+
17
+ datasets:
18
+ - IlyaGusev/gazeta
19
+ - zloelias/lenta-ru
20
+
21
  license: mit
22
+ base_model: cointegrated/rubert-tiny2
23
+
24
  ---
25
+
26
+
27
+ Быстрая модель BERT для расчетов эмбедингов предложений на русском языке. Модель основана на [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) - имеет аналогичные размеры контекста (2048), ембединга (312) и быстродействие.
28
+
29
+
30
+
31
+ ## Использование:
32
+ ```Python
33
+ from sentence_transformers import SentenceTransformer, util
34
+
35
+ model = SentenceTransformer('sergeyzh/rubert-tiny-turbo')
36
+
37
+ sentences = ["привет мир", "hello world", "здравствуй вселенная"]
38
+ embeddings = model.encode(sentences)
39
+ print(util.dot_score(embeddings, embeddings))
40
+ ```
41
+
42
+ ## Метрики
43
+ Оценки модели на бенчмарке [encodechka](https://github.com/avidale/encodechka):
44
+
45
+ | model | CPU | GPU | size | Mean S | Mean S+W | dim |
46
+ |:-----------------------------------|----------:|---------:|---------:|----------:|-----------:|-------:|
47
+ | BAAI/bge-m3 | 523.40 | 22.50 | 2166 | 0.787 | 0.696 | 1024 |
48
+ | intfloat/multilingual-e5-large | 506.80 | 30.80 | 2136 | 0.780 | 0.686 | 1024 |
49
+ | intfloat/multilingual-e5-base | 130.61 | 14.39 | 1061 | 0.761 | 0.669 | 768 |
50
+ | **sergeyzh/rubert-tiny-turbo** | **5.51** |**3.25** |**111** | **0.749**| **0.667** | **312**|
51
+ | intfloat/multilingual-e5-small | 40.86 | 12.09 | 449 | 0.742 | 0.645 | 384 |
52
+ | cointegrated/rubert-tiny2 | 5.51 | 3.25 | 111 | 0.704 | 0.638 | 312 |
53
+
54
+ | model | STS | PI | NLI | SA | TI | IA | IC | ICX | NE1 | NE2 |
55
+ |:-----------------------------------|:---------|:---------|:---------|:---------|:---------|:---------|:---------|:---------|:---------|:---------|
56
+ | BAAI/bge-m3 | 0.864 | 0.749 | 0.510 | 0.819 | 0.973 | 0.792 | 0.809 | 0.783 | 0.240 | 0.422 |
57
+ | intfloat/multilingual-e5-large | 0.862 | 0.727 | 0.473 | 0.810 | 0.979 | 0.798 | 0.819 | 0.773 | 0.224 | 0.374 |
58
+ | intfloat/multilingual-e5-base | 0.835 | 0.704 | 0.459 | 0.796 | 0.964 | 0.783 | 0.802 | 0.738 | 0.235 | 0.376 |
59
+ | sergeyzh/rubert-tiny-turbo |**0.828** |**0.722** |**0.476** |**0.787** |**0.955** |**0.757** |**0.780** |**0.685** |**0.305** |**0.373** |
60
+ | intfloat/multilingual-e5-small | 0.822 | 0.714 | 0.457 | 0.758 | 0.957 | 0.761 | 0.779 | 0.691 | 0.234 | 0.275 |
61
+ | cointegrated/rubert-tiny2 | 0.750 | 0.651 | 0.417 | 0.737 | 0.937 | 0.746 | 0.757 | 0.638 | 0.360 | 0.386 |
62
+
63
+
64
+
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sergeyzh/rubert-tiny-turbo",
3
+ "architectures": [
4
+ "BertModel"
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
+ "initializer_range": 0.02,
14
+ "intermediate_size": 600,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 3,
20
+ "pad_token_id": 0,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 83828
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ef89061050e29f478b5037430789109fece437a938fe1c4ab686828441d107
3
+ size 116781184
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": 2048,
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 6144,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff