AlekseyKorshuk commited on
Commit
4e43110
1 Parent(s): 91396ba

Add SetFit 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 ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 1980 with parameters:
89
+ ```
90
+ {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
91
+ ```
92
+
93
+ **Loss**:
94
+
95
+ `sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
96
+
97
+ Parameters of the fit()-Method:
98
+ ```
99
+ {
100
+ "epochs": 1,
101
+ "evaluation_steps": 0,
102
+ "evaluator": "NoneType",
103
+ "max_grad_norm": 1,
104
+ "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
105
+ "optimizer_params": {
106
+ "lr": 2e-05
107
+ },
108
+ "scheduler": "WarmupLinear",
109
+ "steps_per_epoch": 1980,
110
+ "warmup_steps": 198,
111
+ "weight_decay": 0.01
112
+ }
113
+ ```
114
+
115
+
116
+ ## Full Model Architecture
117
+ ```
118
+ SentenceTransformer(
119
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
120
+ (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})
121
+ )
122
+ ```
123
+
124
+ ## Citing & Authors
125
+
126
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-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": "4.21.2",
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": "4.7.0",
5
+ "pytorch": "1.9.0+cu102"
6
+ }
7
+ }
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365d249edcae03107ac20af14e94254a09e9848b50f2fdd6a6ab3be938899df4
3
+ size 6991
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 sha256:2b3447c978a86be31a9e18416f50f45356ddb160f2b105d9bf7d70d71a4447b5
3
+ size 438014769
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "cls_token": {
11
+ "__type": "AddedToken",
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "do_basic_tokenize": true,
19
+ "do_lower_case": true,
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 512,
37
+ "name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-mpnet-base-v2/",
38
+ "never_split": null,
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "special_tokens_map_file": null,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "MPNetTokenizer",
59
+ "unk_token": {
60
+ "__type": "AddedToken",
61
+ "content": "[UNK]",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ }
67
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff