Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +1 -2
- README.md +37 -2
- config.json +4 -9
- config_sentence_transformers.json +4 -6
- model.safetensors +2 -2
- tokenizer.json +14 -2
- tokenizer_config.json +7 -0
1_Pooling/config.json
CHANGED
@@ -5,6 +5,5 @@
|
|
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 |
-
"include_prompt": true
|
10 |
}
|
|
|
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
CHANGED
@@ -7,7 +7,7 @@ tags:
|
|
7 |
- sentence-similarity
|
8 |
- transformers
|
9 |
datasets:
|
10 |
-
- embedding-data/
|
11 |
---
|
12 |
|
13 |
# arjunsama/mine
|
@@ -82,12 +82,47 @@ print(sentence_embeddings)
|
|
82 |
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=arjunsama/mine)
|
83 |
|
84 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
85 |
|
86 |
## Full Model Architecture
|
87 |
```
|
88 |
SentenceTransformer(
|
89 |
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
90 |
-
(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
|
91 |
)
|
92 |
```
|
93 |
|
|
|
7 |
- sentence-similarity
|
8 |
- transformers
|
9 |
datasets:
|
10 |
+
- embedding-data/sentence-compression
|
11 |
---
|
12 |
|
13 |
# arjunsama/mine
|
|
|
82 |
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=arjunsama/mine)
|
83 |
|
84 |
|
85 |
+
## Training
|
86 |
+
The model was trained with the parameters:
|
87 |
+
|
88 |
+
**DataLoader**:
|
89 |
+
|
90 |
+
`torch.utils.data.dataloader.DataLoader` of length 5469 with parameters:
|
91 |
+
```
|
92 |
+
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
93 |
+
```
|
94 |
+
|
95 |
+
**Loss**:
|
96 |
+
|
97 |
+
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
|
98 |
+
```
|
99 |
+
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
|
100 |
+
```
|
101 |
+
|
102 |
+
Parameters of the fit()-Method:
|
103 |
+
```
|
104 |
+
{
|
105 |
+
"epochs": 10,
|
106 |
+
"evaluation_steps": 0,
|
107 |
+
"evaluator": "NoneType",
|
108 |
+
"max_grad_norm": 1,
|
109 |
+
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
110 |
+
"optimizer_params": {
|
111 |
+
"lr": 2e-05
|
112 |
+
},
|
113 |
+
"scheduler": "WarmupLinear",
|
114 |
+
"steps_per_epoch": null,
|
115 |
+
"warmup_steps": 5469,
|
116 |
+
"weight_decay": 0.01
|
117 |
+
}
|
118 |
+
```
|
119 |
+
|
120 |
|
121 |
## Full Model Architecture
|
122 |
```
|
123 |
SentenceTransformer(
|
124 |
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
125 |
+
(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})
|
126 |
)
|
127 |
```
|
128 |
|
config.json
CHANGED
@@ -1,30 +1,25 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
"hidden_size": 384,
|
11 |
-
"id2label": {
|
12 |
-
"0": "LABEL_0"
|
13 |
-
},
|
14 |
"initializer_range": 0.02,
|
15 |
"intermediate_size": 1536,
|
16 |
-
"label2id": {
|
17 |
-
"LABEL_0": 0
|
18 |
-
},
|
19 |
"layer_norm_eps": 1e-12,
|
20 |
"max_position_embeddings": 512,
|
21 |
"model_type": "bert",
|
22 |
"num_attention_heads": 12,
|
23 |
-
"num_hidden_layers":
|
24 |
"pad_token_id": 0,
|
25 |
"position_embedding_type": "absolute",
|
26 |
"torch_dtype": "float32",
|
27 |
-
"transformers_version": "4.
|
28 |
"type_vocab_size": 2,
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 30522
|
|
|
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": "4.37.2",
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 30522
|
config_sentence_transformers.json
CHANGED
@@ -1,9 +1,7 @@
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
-
"sentence_transformers": "2.
|
4 |
-
"transformers": "4.
|
5 |
-
"pytorch": "2.
|
6 |
-
}
|
7 |
-
"prompts": {},
|
8 |
-
"default_prompt_name": null
|
9 |
}
|
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
+
"sentence_transformers": "2.3.1",
|
4 |
+
"transformers": "4.37.2",
|
5 |
+
"pytorch": "2.2.0+cu121"
|
6 |
+
}
|
|
|
|
|
7 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53cfb0a5e78786bcb47155c5cfba736d0eaff820dbee765bcab62dfdde852f16
|
3 |
+
size 90864192
|
tokenizer.json
CHANGED
@@ -1,7 +1,19 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": "BatchLongest",
|
11 |
+
"direction": "Right",
|
12 |
+
"pad_to_multiple_of": null,
|
13 |
+
"pad_id": 0,
|
14 |
+
"pad_type_id": 0,
|
15 |
+
"pad_token": "[PAD]"
|
16 |
+
},
|
17 |
"added_tokens": [
|
18 |
{
|
19 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -46,12 +46,19 @@
|
|
46 |
"do_basic_tokenize": true,
|
47 |
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
|
|
49 |
"model_max_length": 512,
|
50 |
"never_split": null,
|
|
|
51 |
"pad_token": "[PAD]",
|
|
|
|
|
52 |
"sep_token": "[SEP]",
|
|
|
53 |
"strip_accents": null,
|
54 |
"tokenize_chinese_chars": true,
|
55 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
56 |
"unk_token": "[UNK]"
|
57 |
}
|
|
|
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 |
}
|