hpprc commited on
Commit
f3b4ba3
1 Parent(s): 19d1b48

Upload folder using huggingface_hub

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
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 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ - transformers
8
+ datasets:
9
+ - shunk031/jsnli
10
+ ---
11
+
12
+ # {MODEL_NAME}
13
+
14
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
15
+
16
+ <!--- Describe your model here -->
17
+
18
+ ## Usage (Sentence-Transformers)
19
+
20
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
21
+
22
+ ```
23
+ pip install -U sentence-transformers
24
+ ```
25
+
26
+ Then you can use the model like this:
27
+
28
+ ```python
29
+ from sentence_transformers import SentenceTransformer
30
+ sentences = ["This is an example sentence", "Each sentence is converted"]
31
+
32
+ model = SentenceTransformer('{MODEL_NAME}')
33
+ embeddings = model.encode(sentences)
34
+ print(embeddings)
35
+ ```
36
+
37
+
38
+
39
+ ## Usage (HuggingFace Transformers)
40
+ Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
41
+
42
+ ```python
43
+ from transformers import AutoTokenizer, AutoModel
44
+ import torch
45
+
46
+
47
+ def cls_pooling(model_output, attention_mask):
48
+ return model_output[0][:,0]
49
+
50
+
51
+ # Sentences we want sentence embeddings for
52
+ sentences = ['This is an example sentence', 'Each sentence is converted']
53
+
54
+ # Load model from HuggingFace Hub
55
+ tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
56
+ model = AutoModel.from_pretrained('{MODEL_NAME}')
57
+
58
+ # Tokenize sentences
59
+ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
60
+
61
+ # Compute token embeddings
62
+ with torch.no_grad():
63
+ model_output = model(**encoded_input)
64
+
65
+ # Perform pooling. In this case, cls pooling.
66
+ sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
67
+
68
+ print("Sentence embeddings:")
69
+ print(sentence_embeddings)
70
+ ```
71
+
72
+
73
+
74
+ ## Evaluation Results
75
+
76
+ <!--- Describe how your model was evaluated -->
77
+
78
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
79
+
80
+
81
+
82
+ ## Full Model Architecture
83
+ ```
84
+ SentenceTransformer(
85
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
86
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
87
+ )
88
+ ```
89
+
90
+ ## Citing & Authors
91
+
92
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cl-tohoku/bert-large-japanese-v2",
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": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.28.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 32768
25
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.2",
4
+ "transformers": "4.28.1",
5
+ "pytorch": "2.0.1+cu118"
6
+ }
7
+ }
dev-metrics.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "best-epoch": 0,
3
+ "best-step": 64,
4
+ "best-dev": 84.35700372236889
5
+ }
log.csv ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,step,loss,sts-dev
2
+ 0,0,inf,46.72837224312097
3
+ 0,32,5.49169921875,79.31070160603963
4
+ 0,64,2.51708984375,84.35700372236889
5
+ 0,96,2.013916015625,82.41349585392163
6
+ 0,128,1.83056640625,80.40566982305087
7
+ 0,160,1.715576171875,77.84721366215935
8
+ 0,192,1.650146484375,78.6757653419235
9
+ 0,224,1.568115234375,73.42996624180068
10
+ 0,256,1.55322265625,75.57552162351263
11
+ 1,288,1.490966796875,71.41986682440324
12
+ 1,320,1.37548828125,73.29193104300393
13
+ 1,352,1.33544921875,72.80806281746437
14
+ 1,384,1.350830078125,72.77195292066885
15
+ 1,416,1.353759765625,69.87782142691363
16
+ 1,448,1.33447265625,64.9175102353748
17
+ 1,480,1.309326171875,69.45867633288623
18
+ 1,512,1.31982421875,70.6730909328148
19
+ 1,544,1.29150390625,70.64751383186746
20
+ 2,576,1.212646484375,65.82802791174757
21
+ 2,608,1.11669921875,66.64306435617323
22
+ 2,640,1.14453125,65.48764039746843
23
+ 2,672,1.1185302734375,66.58600028071007
24
+ 2,704,1.123779296875,67.64014437611549
25
+ 2,736,1.103759765625,69.60152425618847
26
+ 2,768,1.141357421875,69.34622506400544
27
+ 2,800,1.270263671875,70.32409725193519
28
+ 2,832,1.221435546875,67.92858244662744
29
+ 3,864,1.0614013671875,66.34717772523808
30
+ 3,896,1.0054931640625,66.87521082007706
31
+ 3,928,1.0040283203125,65.41458032481682
32
+ 3,960,1.0062255859375,65.70913894370779
33
+ 3,992,1.0181884765625,66.46946316417328
34
+ 3,1024,0.996337890625,63.34887069413857
35
+ 3,1056,1.02392578125,65.18104616486384
36
+ 3,1088,0.9970703125,64.49234957916627
37
+ 3,1120,1.0,64.80023992366682
38
+ 4,1152,0.884521484375,65.09789161785304
39
+ 4,1184,0.880615234375,66.50805762020076
40
+ 4,1216,0.886474609375,63.74224407082551
41
+ 4,1248,0.8818359375,63.54117456035738
42
+ 4,1280,0.8819580078125,65.77741134837758
43
+ 4,1312,0.883544921875,66.75449263267615
44
+ 4,1344,0.875732421875,63.99539291809667
45
+ 4,1376,0.9068603515625,64.31698278731722
46
+ 5,1408,0.8865966796875,65.00043435754733
47
+ 5,1440,0.7822265625,64.22602226609517
48
+ 5,1472,0.785400390625,64.0694313946185
49
+ 5,1504,0.7928466796875,63.40049229004234
50
+ 5,1536,0.784912109375,62.86333382743011
51
+ 5,1568,0.794189453125,64.06125094235347
52
+ 5,1600,0.810546875,62.99456391252577
53
+ 5,1632,0.8006591796875,62.3648377584635
54
+ 5,1664,0.7896728515625,64.00460895931644
55
+ 6,1696,0.7900390625,64.12996526496609
56
+ 6,1728,0.720703125,64.04989699764432
57
+ 6,1760,0.7353515625,62.60633883039293
58
+ 6,1792,0.735595703125,62.39235079765329
59
+ 6,1824,0.72314453125,62.836391633071166
60
+ 6,1856,0.7305908203125,63.51677689636537
61
+ 6,1888,0.729248046875,63.40423279523494
62
+ 6,1920,0.7313232421875,63.03712185206447
63
+ 6,1952,0.733154296875,63.04729553320853
64
+ 7,1984,0.699462890625,62.68467625961607
65
+ 7,2016,0.70556640625,62.67148071717765
66
+ 7,2048,0.69970703125,62.75529368448359
modules.json ADDED
@@ -0,0 +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
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8484e8d52ac2e6d9a263662ac4d11932518ee09ed7566ee43b9a044971fff71
3
+ size 1349897965
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 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
sts-metrics.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "jsick": 83.05096544584796,
3
+ "jsts-val": 83.07326084142757,
4
+ "jsts-train": 79.61292079857638,
5
+ "avg": 81.91238236195063
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "do_subword_tokenize": true,
6
+ "do_word_tokenize": true,
7
+ "jumanpp_kwargs": null,
8
+ "mask_token": "[MASK]",
9
+ "mecab_kwargs": {
10
+ "mecab_dic": "unidic_lite"
11
+ },
12
+ "model_max_length": 512,
13
+ "never_split": null,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "subword_tokenizer_type": "wordpiece",
17
+ "sudachi_kwargs": null,
18
+ "tokenizer_class": "BertJapaneseTokenizer",
19
+ "unk_token": "[UNK]",
20
+ "word_tokenizer_type": "mecab"
21
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff