tubyneto commited on
Commit
69ae6dd
1 Parent(s): db79de0

Add new SentenceTransformer model.

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
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 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
+ # tubyneto/crowdedflowertunedbertt
11
+
12
+ 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.
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('tubyneto/crowdedflowertunedbertt')
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=tubyneto/crowdedflowertunedbertt)
42
+
43
+
44
+ ## Training
45
+ The model was trained with the parameters:
46
+
47
+ **DataLoader**:
48
+
49
+ `torch.utils.data.dataloader.DataLoader` of length 916 with parameters:
50
+ ```
51
+ {'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
52
+ ```
53
+
54
+ **Loss**:
55
+
56
+ `sentence_transformers.losses.ContrastiveLoss.ContrastiveLoss` with parameters:
57
+ ```
58
+ {'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True}
59
+ ```
60
+
61
+ Parameters of the fit()-Method:
62
+ ```
63
+ {
64
+ "epochs": 10,
65
+ "evaluation_steps": 0,
66
+ "evaluator": "NoneType",
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": 10000,
75
+ "weight_decay": 0.01
76
+ }
77
+ ```
78
+
79
+
80
+ ## Full Model Architecture
81
+ ```
82
+ SentenceTransformer(
83
+ (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel
84
+ (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})
85
+ (2): Normalize()
86
+ )
87
+ ```
88
+
89
+ ## Citing & Authors
90
+
91
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "C:\\Users\\Tuby Neto/.cache\\torch\\sentence_transformers\\sentence-transformers_all-mpnet-base-v2\\",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.22.0",
23
+ "vocab_size": 30527
24
+ }
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
+ }
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
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3627c3815984fa12637f4d2011b5f5d6b3e5120409f1893982e155e840b1cdb
3
+ size 438011953
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 384,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "[UNK]"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "do_lower_case": true,
5
+ "eos_token": "</s>",
6
+ "mask_token": "<mask>",
7
+ "model_max_length": 512,
8
+ "name_or_path": "C:\\Users\\Tuby Neto/.cache\\torch\\sentence_transformers\\sentence-transformers_all-mpnet-base-v2\\",
9
+ "pad_token": "<pad>",
10
+ "sep_token": "</s>",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "MPNetTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff