Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +1 -1
- README.md +3 -3
- config.json +13 -11
- model.safetensors +2 -2
- sentence_bert_config.json +1 -1
- special_tokens_map.json +5 -19
- tokenizer.json +0 -0
- tokenizer_config.json +17 -25
- vocab.txt +0 -5
1_Pooling/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"word_embedding_dimension":
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
|
|
1 |
{
|
2 |
+
"word_embedding_dimension": 384,
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
README.md
CHANGED
@@ -10,7 +10,7 @@ tags:
|
|
10 |
|
11 |
# HSR-HF/sts-rf-bc-contrastive
|
12 |
|
13 |
-
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a
|
14 |
|
15 |
<!--- Describe your model here -->
|
16 |
|
@@ -81,8 +81,8 @@ Parameters of the fit()-Method:
|
|
81 |
## Full Model Architecture
|
82 |
```
|
83 |
SentenceTransformer(
|
84 |
-
(0): Transformer({'max_seq_length':
|
85 |
-
(1): Pooling({'word_embedding_dimension':
|
86 |
(2): Normalize()
|
87 |
(dropout): Dropout(
|
88 |
(dropout_layer): Dropout(p=0.1, inplace=False)
|
|
|
10 |
|
11 |
# HSR-HF/sts-rf-bc-contrastive
|
12 |
|
13 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
14 |
|
15 |
<!--- Describe your model here -->
|
16 |
|
|
|
81 |
## Full Model Architecture
|
82 |
```
|
83 |
SentenceTransformer(
|
84 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
85 |
+
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
86 |
(2): Normalize()
|
87 |
(dropout): Dropout(
|
88 |
(dropout_layer): Dropout(p=0.1, inplace=False)
|
config.json
CHANGED
@@ -1,24 +1,26 @@
|
|
1 |
{
|
2 |
"_name_or_path": "/content/output_train",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"
|
8 |
-
"
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size":
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size":
|
14 |
-
"layer_norm_eps": 1e-
|
15 |
-
"max_position_embeddings":
|
16 |
-
"model_type": "
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 12,
|
19 |
-
"pad_token_id":
|
20 |
-
"
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.40.2",
|
23 |
-
"
|
|
|
|
|
24 |
}
|
|
|
1 |
{
|
2 |
"_name_or_path": "/content/output_train",
|
3 |
"architectures": [
|
4 |
+
"BertModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 384,
|
12 |
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.40.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7cbbfbb6667f8628c544b976d2dd0ad217cfae58d320be22c9e60cd8f30d8f5
|
3 |
+
size 133462128
|
sentence_bert_config.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"max_seq_length":
|
3 |
"do_lower_case": false
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"max_seq_length": 128,
|
3 |
"do_lower_case": false
|
4 |
}
|
special_tokens_map.json
CHANGED
@@ -1,41 +1,27 @@
|
|
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": "
|
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": "
|
25 |
-
"lstrip":
|
26 |
"normalized": false,
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
"pad_token": {
|
31 |
-
"content": "
|
32 |
"lstrip": false,
|
33 |
"normalized": false,
|
34 |
"rstrip": false,
|
35 |
"single_word": false
|
36 |
},
|
37 |
"sep_token": {
|
38 |
-
"content": "
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
41 |
"rstrip": false,
|
|
|
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,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,71 +1,63 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": true,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"104": {
|
36 |
-
"content": "[UNK]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
},
|
43 |
-
"
|
44 |
-
"content": "
|
45 |
-
"lstrip":
|
46 |
"normalized": false,
|
47 |
"rstrip": false,
|
48 |
"single_word": false,
|
49 |
"special": true
|
50 |
}
|
51 |
},
|
52 |
-
"bos_token": "<s>",
|
53 |
"clean_up_tokenization_spaces": true,
|
54 |
-
"cls_token": "
|
|
|
55 |
"do_lower_case": true,
|
56 |
-
"
|
57 |
-
"mask_token": "<mask>",
|
58 |
"max_length": 128,
|
59 |
"model_max_length": 512,
|
|
|
60 |
"pad_to_multiple_of": null,
|
61 |
-
"pad_token": "
|
62 |
"pad_token_type_id": 0,
|
63 |
"padding_side": "right",
|
64 |
-
"sep_token": "
|
65 |
"stride": 0,
|
66 |
"strip_accents": null,
|
67 |
"tokenize_chinese_chars": true,
|
68 |
-
"tokenizer_class": "
|
69 |
"truncation_side": "right",
|
70 |
"truncation_strategy": "longest_first",
|
71 |
"unk_token": "[UNK]"
|
|
|
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 |
+
"mask_token": "[MASK]",
|
|
|
49 |
"max_length": 128,
|
50 |
"model_max_length": 512,
|
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]"
|
vocab.txt
CHANGED
@@ -1,7 +1,3 @@
|
|
1 |
-
<s>
|
2 |
-
<pad>
|
3 |
-
</s>
|
4 |
-
<unk>
|
5 |
[PAD]
|
6 |
[unused0]
|
7 |
[unused1]
|
@@ -30524,4 +30520,3 @@ necessitated
|
|
30524 |
##:
|
30525 |
##?
|
30526 |
##~
|
30527 |
-
<mask>
|
|
|
|
|
|
|
|
|
|
|
1 |
[PAD]
|
2 |
[unused0]
|
3 |
[unused1]
|
|
|
30520 |
##:
|
30521 |
##?
|
30522 |
##~
|
|