w11wo commited on
Commit
e151603
1 Parent(s): e0e48cf

Add new SentenceTransformer model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
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
+ }
README.md CHANGED
@@ -1,3 +1,129 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ - transformers
8
+
9
  ---
10
+
11
+ # {MODEL_NAME}
12
+
13
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
14
+
15
+ <!--- Describe your model here -->
16
+
17
+ ## Usage (Sentence-Transformers)
18
+
19
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
20
+
21
+ ```
22
+ pip install -U sentence-transformers
23
+ ```
24
+
25
+ Then you can use the model like this:
26
+
27
+ ```python
28
+ from sentence_transformers import SentenceTransformer
29
+ sentences = ["This is an example sentence", "Each sentence is converted"]
30
+
31
+ model = SentenceTransformer('{MODEL_NAME}')
32
+ embeddings = model.encode(sentences)
33
+ print(embeddings)
34
+ ```
35
+
36
+
37
+
38
+ ## Usage (HuggingFace Transformers)
39
+ 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.
40
+
41
+ ```python
42
+ from transformers import AutoTokenizer, AutoModel
43
+ import torch
44
+
45
+
46
+ #Mean Pooling - Take attention mask into account for correct averaging
47
+ def mean_pooling(model_output, attention_mask):
48
+ token_embeddings = model_output[0] #First element of model_output contains all token embeddings
49
+ input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
50
+ return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
51
+
52
+
53
+ # Sentences we want sentence embeddings for
54
+ sentences = ['This is an example sentence', 'Each sentence is converted']
55
+
56
+ # Load model from HuggingFace Hub
57
+ tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
58
+ model = AutoModel.from_pretrained('{MODEL_NAME}')
59
+
60
+ # Tokenize sentences
61
+ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
62
+
63
+ # Compute token embeddings
64
+ with torch.no_grad():
65
+ model_output = model(**encoded_input)
66
+
67
+ # Perform pooling. In this case, mean pooling.
68
+ sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
69
+
70
+ print("Sentence embeddings:")
71
+ print(sentence_embeddings)
72
+ ```
73
+
74
+
75
+
76
+ ## Evaluation Results
77
+
78
+ <!--- Describe how your model was evaluated -->
79
+
80
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
81
+
82
+
83
+ ## Training
84
+ The model was trained with the parameters:
85
+
86
+ **DataLoader**:
87
+
88
+ `torch.utils.data.dataloader.DataLoader` of length 782 with parameters:
89
+ ```
90
+ {'batch_size': 128, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
91
+ ```
92
+
93
+ **Loss**:
94
+
95
+ `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
96
+ ```
97
+ {'scale': 20.0, 'similarity_fct': 'cos_sim'}
98
+ ```
99
+
100
+ Parameters of the fit()-Method:
101
+ ```
102
+ {
103
+ "epochs": 1,
104
+ "evaluation_steps": 0,
105
+ "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
106
+ "max_grad_norm": 1,
107
+ "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
108
+ "optimizer_params": {
109
+ "lr": 3e-05
110
+ },
111
+ "scheduler": "WarmupLinear",
112
+ "steps_per_epoch": null,
113
+ "warmup_steps": 10000,
114
+ "weight_decay": 0.01
115
+ }
116
+ ```
117
+
118
+
119
+ ## Full Model Architecture
120
+ ```
121
+ SentenceTransformer(
122
+ (0): Transformer({'max_seq_length': 32, 'do_lower_case': False}) with Transformer model: BertModel
123
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
124
+ )
125
+ ```
126
+
127
+ ## Citing & Authors
128
+
129
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "indobenchmark/indobert-base-p1",
3
+ "_num_labels": 5,
4
+ "architectures": [
5
+ "BertModel"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "bert",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 0,
36
+ "pooler_fc_size": 768,
37
+ "pooler_num_attention_heads": 12,
38
+ "pooler_num_fc_layers": 3,
39
+ "pooler_size_per_head": 128,
40
+ "pooler_type": "first_token_transform",
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.29.2",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 50000
47
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.2",
4
+ "transformers": "4.29.2",
5
+ "pytorch": "2.0.1+cu118"
6
+ }
7
+ }
eval/similarity_evaluation_results.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ 0,-1,0.6210425880472122,0.6154181874927932,0.6325135591051501,0.629094195339931,0.6314686880278273,0.6279293037763658,0.3827246918814826,0.36823825371127544
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 sha256:8137eb18a9480e136dd4a1c247532f6925575b76792f73c7699c8ae10803a4ea
3
+ size 497836589
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 32,
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff