ramnathv commited on
Commit
4751a1a
1 Parent(s): 4218f36

Add new SentenceTransformer model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
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
+ }
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+
8
+ ---
9
+
10
+ # {MODEL_NAME}
11
+
12
+ 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.
13
+
14
+ <!--- Describe your model here -->
15
+
16
+ ## Usage (Sentence-Transformers)
17
+
18
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
19
+
20
+ ```
21
+ pip install -U sentence-transformers
22
+ ```
23
+
24
+ Then you can use the model like this:
25
+
26
+ ```python
27
+ from sentence_transformers import SentenceTransformer
28
+ sentences = ["This is an example sentence", "Each sentence is converted"]
29
+
30
+ model = SentenceTransformer('{MODEL_NAME}')
31
+ embeddings = model.encode(sentences)
32
+ print(embeddings)
33
+ ```
34
+
35
+
36
+
37
+ ## Evaluation Results
38
+
39
+ <!--- Describe how your model was evaluated -->
40
+
41
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
42
+
43
+
44
+ ## Training
45
+ The model was trained with the parameters:
46
+
47
+ **DataLoader**:
48
+
49
+ `torch.utils.data.dataloader.DataLoader` of length 30 with parameters:
50
+ ```
51
+ {'batch_size': 10, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
52
+ ```
53
+
54
+ **Loss**:
55
+
56
+ `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
57
+ ```
58
+ {'scale': 20.0, 'similarity_fct': 'cos_sim'}
59
+ ```
60
+
61
+ Parameters of the fit()-Method:
62
+ ```
63
+ {
64
+ "epochs": 10,
65
+ "evaluation_steps": 50,
66
+ "evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
67
+ "max_grad_norm": 1,
68
+ "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
69
+ "optimizer_params": {
70
+ "lr": 2e-05
71
+ },
72
+ "scheduler": "WarmupLinear",
73
+ "steps_per_epoch": null,
74
+ "warmup_steps": 30,
75
+ "weight_decay": 0.01
76
+ }
77
+ ```
78
+
79
+
80
+ ## Full Model Architecture
81
+ ```
82
+ SentenceTransformer(
83
+ (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
84
+ (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})
85
+ (2): Normalize()
86
+ )
87
+ ```
88
+
89
+ ## Citing & Authors
90
+
91
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
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": 6,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.35.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.6.1",
5
+ "pytorch": "1.8.1"
6
+ }
7
+ }
eval/Information-Retrieval_evaluation_results.csv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100,dot_score-Accuracy@1,dot_score-Accuracy@3,dot_score-Accuracy@5,dot_score-Accuracy@10,dot_score-Precision@1,dot_score-Recall@1,dot_score-Precision@3,dot_score-Recall@3,dot_score-Precision@5,dot_score-Recall@5,dot_score-Precision@10,dot_score-Recall@10,dot_score-MRR@10,dot_score-NDCG@10,dot_score-MAP@100
2
+ 0,-1,0.92,0.95,0.96,0.98,0.92,0.92,0.31666666666666665,0.95,0.19199999999999995,0.96,0.09799999999999998,0.98,0.9389285714285716,0.9488207658565767,0.939354292049414,0.92,0.95,0.96,0.98,0.92,0.92,0.31666666666666665,0.95,0.19199999999999995,0.96,0.09799999999999998,0.98,0.9389285714285716,0.9488207658565767,0.939354292049414
3
+ 1,-1,0.92,0.95,0.97,0.98,0.92,0.92,0.31666666666666665,0.95,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9397619047619048,0.9495654595662303,0.9402171105730429,0.92,0.95,0.97,0.98,0.92,0.92,0.31666666666666665,0.95,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9397619047619048,0.9495654595662303,0.9402171105730429
4
+ 2,-1,0.93,0.96,0.96,0.98,0.93,0.93,0.31999999999999995,0.96,0.19199999999999995,0.96,0.09799999999999998,0.98,0.9447619047619048,0.953204702740128,0.9452284362020671,0.93,0.96,0.96,0.98,0.93,0.93,0.31999999999999995,0.96,0.19199999999999995,0.96,0.09799999999999998,0.98,0.9447619047619048,0.953204702740128,0.9452284362020671
5
+ 3,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420000000000001,0.9513584925505694,0.9425035577449371,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420000000000001,0.9513584925505694,0.9425035577449371
6
+ 4,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427432155657962,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427432155657962
7
+ 5,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425967261904762,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425967261904762
8
+ 6,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427683013503909,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427683013503909
9
+ 7,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427683013503909,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427683013503909
10
+ 8,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425897299218196,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425897299218196
11
+ 9,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425897299218196,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425897299218196
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5361cb8adf099468f69c22aee86d75b41a54ad28a7e02e42421e87e8c6797705
3
+ size 90864192
modules.json ADDED
@@ -0,0 +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
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 256,
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff