Piotr Rybak commited on
Commit
0339799
1 Parent(s): cf4a256

upload model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
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
+ }
2_Dense/config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"in_features": 1024, "out_features": 512, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}
2_Dense/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0752e7dc2a63048a40e51855251f1a23a858061e84dce5a229c5700fc99f6d5
3
+ size 2100263
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
+ # {MODEL_NAME}
10
+
11
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search.
12
+
13
+ <!--- Describe your model here -->
14
+
15
+ ## Usage (Sentence-Transformers)
16
+
17
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
18
+
19
+ ```
20
+ pip install -U sentence-transformers
21
+ ```
22
+
23
+ Then you can use the model like this:
24
+
25
+ ```python
26
+ from sentence_transformers import SentenceTransformer
27
+ sentences = ["This is an example sentence", "Each sentence is converted"]
28
+
29
+ model = SentenceTransformer('{MODEL_NAME}')
30
+ embeddings = model.encode(sentences)
31
+ print(embeddings)
32
+ ```
33
+
34
+
35
+
36
+ ## Evaluation Results
37
+
38
+ <!--- Describe how your model was evaluated -->
39
+
40
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
41
+
42
+
43
+ ## Training
44
+ The model was trained with the parameters:
45
+
46
+ **DataLoader**:
47
+
48
+ `torch.utils.data.dataloader.DataLoader` of length 6098 with parameters:
49
+ ```
50
+ {'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
51
+ ```
52
+
53
+ **Loss**:
54
+
55
+ `sentence_transformers.losses.ContrastiveLoss.ContrastiveLoss` with parameters:
56
+ ```
57
+ {'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True}
58
+ ```
59
+
60
+ Parameters of the fit()-Method:
61
+ ```
62
+ {
63
+ "callback": null,
64
+ "epochs": 5,
65
+ "evaluation_steps": 0,
66
+ "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
67
+ "max_grad_norm": 1,
68
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
69
+ "optimizer_params": {
70
+ "lr": 1e-05
71
+ },
72
+ "scheduler": "WarmupLinear",
73
+ "steps_per_epoch": null,
74
+ "warmup_steps": 3049,
75
+ "weight_decay": 0.01
76
+ }
77
+ ```
78
+
79
+
80
+ ## Full Model Architecture
81
+ ```
82
+ SentenceTransformer(
83
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
84
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
85
+ (2): Dense({'in_features': 1024, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
86
+ )
87
+ ```
88
+
89
+ ## Citing & Authors
90
+
91
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allegro/herbert-large-cased",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 1,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "tokenizer_class": "HerbertTokenizerFast",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.9.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 50000
32
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.9.2",
5
+ "pytorch": "1.9.0"
6
+ }
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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_Dense",
18
+ "type": "sentence_transformers.models.Dense"
19
+ }
20
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca627b9ed29a2cbee16bfd37b81592683f244ed30cce8a9b01df2a1ae247f96
3
+ size 1420514545
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 @@
 
 
1
+ {"bos_token": "<s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "sep_token": "</s>", "do_lowercase_and_remove_accent": false, "bos_token": "<s>", "additional_special_tokens": [], "model_max_length": 512, "special_tokens_map_file": "/home/jupyter/.cache/huggingface/transformers/7e8fe8852a1ff7e03195cb41fac16af837f8c14a34a61850b02a7395eb294f00.b8e113717eb1828d09e47de853cf49c8fad05ebdce24df2614cd942dc23e2a77", "name_or_path": "allegro/herbert-large-cased", "lang2id": null, "id2lang": null, "tokenizer_file": null, "tokenizer_class": "HerbertTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff