Hugging Face's logo

Shakhovak
/
tiny_sent_transformer

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:13690
loss:ContrastiveLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
Shakhovak commited on
Commit
92c1369
•
1 Parent(s): f961231

End of training

Browse files
Files changed (10) hide show
  1. 1_Pooling/config.json +9 -9
  2. README.md +0 -0
  3. config.json +27 -27
  4. config_sentence_transformers.json +9 -9
  5. model.safetensors +1 -1
  6. modules.json +19 -19
  7. sentence_bert_config.json +3 -3
  8. special_tokens_map.json +37 -37
  9. tokenizer_config.json +64 -64
  10. training_args.bin +2 -2
1_Pooling/config.json CHANGED
@@ -1,10 +1,10 @@
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
- "pooling_mode_weightedmean_tokens": false,
8
- "pooling_mode_lasttoken": false,
9
- "include_prompt": true
10
  }
 
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
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
  }
README.md CHANGED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -1,27 +1,27 @@
1
- {
2
- "_name_or_path": "cointegrated/rubert-tiny2",
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": "4.44.2",
24
- "type_vocab_size": 2,
25
- "use_cache": true,
26
- "vocab_size": 83828
27
- }
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
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": "4.44.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 83828
27
+ }
config_sentence_transformers.json CHANGED
@@ -1,10 +1,10 @@
1
- {
2
- "__version__": {
3
- "sentence_transformers": "3.0.1",
4
- "transformers": "4.44.2",
5
- "pytorch": "2.0.1+cu118"
6
- },
7
- "prompts": {},
8
- "default_prompt_name": null,
9
- "similarity_fn_name": null
10
  }
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.1.0",
4
+ "transformers": "4.44.2",
5
+ "pytorch": "2.4.1+cu118"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec23966a26643fc171bf1b117f44e3f1b14d8351e5c429f20d71035e428e09e7
3
  size 116781184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57d6d7f1b6de106a6f38fd47bf38b428526c6d24894d42a0ce8e104b7d66e69
3
  size 116781184
modules.json CHANGED
@@ -1,20 +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
  ]
 
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 CHANGED
@@ -1,4 +1,4 @@
1
- {
2
- "max_seq_length": 2048,
3
- "do_lower_case": false
4
  }
 
1
+ {
2
+ "max_seq_length": 2048,
3
+ "do_lower_case": false
4
  }
special_tokens_map.json CHANGED
@@ -1,37 +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
- }
 
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_config.json CHANGED
@@ -1,64 +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
- }
 
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f8d061bf020f0d57a8f3962a913933240693316030cb7d5db8fecc938511acf
3
- size 5051
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea9dc835ea4084259faed880db5dc5ca6dc68cbebd09d04f8f2b4b4907bce1a
3
+ size 5496