Hugging Face's logo

BlackKakapo
/
cupidon-tiny-ro

Sentence Similarity
sentence-transformers
ONNX
Safetensors
OpenVINO
Transformers
Romanian
bert
feature-extraction
text-embeddings-inference
Model card Files
xet
 Community
2
BlackKakapo commited on
Commit
699daa0
·
verified ·
1 Parent(s): 474f2ae

Upload 9 files

Browse files
Files changed (8) hide show
  1. 1_Pooling/config.json +9 -9
  2. config.json +25 -27
  3. config_sentence_transformers.json +9 -13
  4. modules.json +13 -13
  5. sentence_bert_config.json +3 -3
  6. special_tokens_map.json +37 -51
  7. tokenizer.json +2 -2
  8. tokenizer_config.json +65 -64
1_Pooling/config.json CHANGED
@@ -1,10 +1,10 @@
1
- {
2
- "word_embedding_dimension": 768,
3
- "pooling_mode_cls_token": false,
4
- "pooling_mode_mean_tokens": true,
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": 128,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
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
  }
config.json CHANGED
@@ -1,27 +1,25 @@
1
- {
2
- "architectures": [
3
- "XLMRobertaModel"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 0,
7
- "classifier_dropout": null,
8
- "eos_token_id": 2,
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-05,
16
- "max_position_embeddings": 514,
17
- "model_type": "xlm-roberta",
18
- "num_attention_heads": 12,
19
- "num_hidden_layers": 12,
20
- "output_past": true,
21
- "pad_token_id": 1,
22
- "position_embedding_type": "absolute",
23
- "transformers_version": "4.53.3",
24
- "type_vocab_size": 1,
25
- "use_cache": true,
26
- "vocab_size": 250002
27
- }
 
1
+ {
2
+ "_name_or_path": "sentence-transformers-testing/stsb-bert-tiny-safetensors",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 512,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.49.0",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
 
 
config_sentence_transformers.json CHANGED
@@ -1,14 +1,10 @@
1
- {
2
- "__version__": {
3
- "sentence_transformers": "5.1.0",
4
- "transformers": "4.53.3",
5
- "pytorch": "2.5.1+cu121"
6
- },
7
- "prompts": {
8
- "query": "",
9
- "document": ""
10
- },
11
- "default_prompt_name": null,
12
- "similarity_fn_name": "cosine",
13
- "model_type": "SentenceTransformer"
14
  }
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.4.1",
4
+ "transformers": "4.49.0",
5
+ "pytorch": "2.6.0+cu118"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
 
 
 
 
10
  }
modules.json CHANGED
@@ -1,14 +1,14 @@
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
  ]
 
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
  ]
sentence_bert_config.json CHANGED
@@ -1,4 +1,4 @@
1
- {
2
- "max_seq_length": 128,
3
- "do_lower_case": false
4
  }
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
  }
special_tokens_map.json CHANGED
@@ -1,51 +1,37 @@
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": false,
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
- }
 
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c2ccb33b55c4d157419a2105d6e033f7514c2baa6306471c56b86ab02787613
3
- size 17083053
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f1def9b9391fdabe028cd3f3fcc4efd34e5d1f08c3bf2de513ebb5911a1854
3
+ size 711649
tokenizer_config.json CHANGED
@@ -1,64 +1,65 @@
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": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": false,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
- "extra_special_tokens": {},
49
- "full_tokenizer_file": null,
50
- "mask_token": "<mask>",
51
- "max_length": 128,
52
- "model_max_length": 128,
53
- "pad_to_multiple_of": null,
54
- "pad_token": "<pad>",
55
- "pad_token_type_id": 0,
56
- "padding_side": "right",
57
- "sep_token": "</s>",
58
- "sp_model_kwargs": {},
59
- "stride": 0,
60
- "tokenizer_class": "XLMRobertaTokenizerFast",
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }