austinpatrickm
commited on
Commit
•
f2ebb03
1
Parent(s):
24ddc9f
Upload 12 files
Browse files- 1_Pooling/config.json +7 -0
- README.md +91 -0
- config.json +32 -0
- config_sentence_transformers.json +7 -0
- eval/Information-Retrieval_evaluation_results.csv +19 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
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 |
+
# {MODEL_NAME}
|
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('{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 429 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": 2,
|
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": 85,
|
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': True}) with Transformer model: BertModel
|
84 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/BAAI_bge-base-en/",
|
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": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.35.2",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 30522
|
32 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.28.1",
|
5 |
+
"pytorch": "1.13.0+cu117"
|
6 |
+
}
|
7 |
+
}
|
eval/Information-Retrieval_evaluation_results.csv
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
0,50,0.6166163843119054,0.8036667440241355,0.8616848456718497,0.9194708749129729,0.6166163843119054,0.6166163843119054,0.2678889146747118,0.8036667440241355,0.1723369691343699,0.8616848456718497,0.09194708749129728,0.9194708749129729,0.7214442271067947,0.7696294510202493,0.7248933413337,0.6166163843119054,0.8036667440241355,0.8616848456718497,0.9194708749129729,0.6166163843119054,0.6166163843119054,0.2678889146747118,0.8036667440241355,0.1723369691343699,0.8616848456718497,0.09194708749129728,0.9194708749129729,0.7214442271067947,0.7696294510202493,0.7248933413337
|
3 |
+
0,100,0.6015316778834997,0.7957762822000464,0.8491529357159434,0.9060106753307032,0.6015316778834997,0.6015316778834997,0.2652587607333488,0.7957762822000464,0.16983058714318866,0.8491529357159434,0.09060106753307032,0.9060106753307032,0.7084257018348458,0.756636406797182,0.7120742321882497,0.6015316778834997,0.7957762822000464,0.8491529357159434,0.9060106753307032,0.6015316778834997,0.6015316778834997,0.2652587607333488,0.7957762822000464,0.16983058714318866,0.8491529357159434,0.09060106753307032,0.9060106753307032,0.7084257018348458,0.756636406797182,0.7120742321882497
|
4 |
+
0,150,0.6066372708284985,0.8097006265954978,0.8681828730563936,0.9236481782316083,0.6066372708284985,0.6066372708284985,0.2699002088651659,0.8097006265954978,0.17363657461127874,0.8681828730563936,0.09236481782316083,0.9236481782316083,0.7193634953788131,0.7692876412701444,0.7223997694262606,0.6066372708284985,0.8097006265954978,0.8681828730563936,0.9236481782316083,0.6066372708284985,0.6066372708284985,0.2699002088651659,0.8097006265954978,0.17363657461127874,0.8681828730563936,0.09236481782316083,0.9236481782316083,0.7193634953788131,0.7692876412701444,0.7223997694262606
|
5 |
+
0,200,0.5855186818287306,0.7920631236945928,0.8570433975400324,0.9136690647482014,0.5855186818287306,0.5855186818287306,0.26402104123153086,0.7920631236945928,0.17140867950800648,0.8570433975400324,0.09136690647482014,0.9136690647482014,0.7011512449026958,0.7530625014060075,0.7046435287799051,0.5855186818287306,0.7920631236945928,0.8570433975400324,0.9136690647482014,0.5855186818287306,0.5855186818287306,0.26402104123153086,0.7920631236945928,0.17140867950800648,0.8570433975400324,0.09136690647482014,0.9136690647482014,0.7011512449026958,0.7530625014060075,0.7046435287799051
|
6 |
+
0,250,0.6460895799489441,0.8410304014852634,0.8925504757484335,0.9375725226270596,0.6460895799489441,0.6460895799489441,0.28034346716175446,0.8410304014852634,0.17851009514968671,0.8925504757484335,0.09375725226270597,0.9375725226270596,0.7525162358592391,0.7979616067439503,0.7550856784529035,0.6460895799489441,0.8410304014852634,0.8925504757484335,0.9375725226270596,0.6460895799489441,0.6460895799489441,0.28034346716175446,0.8410304014852634,0.17851009514968671,0.8925504757484335,0.09375725226270597,0.9375725226270596,0.7525162358592391,0.7979616067439503,0.7550856784529035
|
7 |
+
0,300,0.6386632629380367,0.8338361568809468,0.8925504757484335,0.9398932466929683,0.6386632629380367,0.6386632629380367,0.27794538562698223,0.8338361568809468,0.1785100951496867,0.8925504757484335,0.09398932466929683,0.9398932466929683,0.7472999480599858,0.794514612457204,0.7497253756129607,0.6386632629380367,0.8338361568809468,0.8925504757484335,0.9398932466929683,0.6386632629380367,0.6386632629380367,0.27794538562698223,0.8338361568809468,0.1785100951496867,0.8925504757484335,0.09398932466929683,0.9398932466929683,0.7472999480599858,0.794514612457204,0.7497253756129607
|
8 |
+
0,350,0.6307728011139475,0.8319795776282201,0.8862845207704804,0.9345555813413785,0.6307728011139475,0.6307728011139475,0.2773265258760733,0.8319795776282201,0.17725690415409606,0.8862845207704804,0.09345555813413785,0.9345555813413785,0.7408764232853354,0.7884126558012902,0.7436443700048466,0.6307728011139475,0.8319795776282201,0.8862845207704804,0.9345555813413785,0.6307728011139475,0.6307728011139475,0.2773265258760733,0.8319795776282201,0.17725690415409606,0.8862845207704804,0.09345555813413785,0.9345555813413785,0.7408764232853354,0.7884126558012902,0.7436443700048466
|
9 |
+
0,400,0.6296124390809933,0.8298909259689023,0.8811789278254816,0.9303782780227431,0.6296124390809933,0.6296124390809933,0.2766303086563008,0.8298909259689023,0.1762357855650963,0.8811789278254816,0.0930378278022743,0.9303782780227431,0.7389697458622968,0.785959494303346,0.7419620419819033,0.6296124390809933,0.8298909259689023,0.8811789278254816,0.9303782780227431,0.6296124390809933,0.6296124390809933,0.2766303086563008,0.8298909259689023,0.1762357855650963,0.8811789278254816,0.0930378278022743,0.9303782780227431,0.7389697458622968,0.785959494303346,0.7419620419819033
|
10 |
+
0,-1,0.6351821768391738,0.8349965189139011,0.8844279415177535,0.9359480157809237,0.6351821768391738,0.6351821768391738,0.27833217297130036,0.8349965189139011,0.1768855883035507,0.8844279415177535,0.09359480157809236,0.9359480157809237,0.743613312115285,0.7907047745203429,0.7462498688590583,0.6351821768391738,0.8349965189139011,0.8844279415177535,0.9359480157809237,0.6351821768391738,0.6351821768391738,0.27833217297130036,0.8349965189139011,0.1768855883035507,0.8844279415177535,0.09359480157809236,0.9359480157809237,0.743613312115285,0.7907047745203429,0.7462498688590583
|
11 |
+
1,50,0.6449292179159898,0.841726618705036,0.8916221861220701,0.9415177535391042,0.6449292179159898,0.6449292179159898,0.2805755395683453,0.841726618705036,0.178324437224414,0.8916221861220701,0.09415177535391042,0.9415177535391042,0.7528450051019094,0.7991392863051507,0.7552901139772051,0.6449292179159898,0.841726618705036,0.8916221861220701,0.9415177535391042,0.6449292179159898,0.6449292179159898,0.2805755395683453,0.841726618705036,0.178324437224414,0.8916221861220701,0.09415177535391042,0.9415177535391042,0.7528450051019094,0.7991392863051507,0.7552901139772051
|
12 |
+
1,100,0.6481782316082618,0.8426549083313994,0.8913901137154793,0.9403573915061499,0.6481782316082618,0.6481782316082618,0.28088496944379976,0.8426549083313994,0.17827802274309584,0.8913901137154793,0.09403573915061497,0.9403573915061499,0.7546455922819353,0.8001924297911145,0.7571884716714739,0.6481782316082618,0.8426549083313994,0.8913901137154793,0.9403573915061499,0.6481782316082618,0.6481782316082618,0.28088496944379976,0.8426549083313994,0.17827802274309584,0.8913901137154793,0.09403573915061497,0.9403573915061499,0.7546455922819353,0.8001924297911145,0.7571884716714739
|
13 |
+
1,150,0.6405198421907635,0.8373172429798097,0.8855883035507078,0.9357159433743328,0.6405198421907635,0.6405198421907635,0.2791057476599365,0.8373172429798097,0.1771176607101415,0.8855883035507078,0.09357159433743327,0.9357159433743328,0.7479839170138551,0.7940163464161489,0.7506964079592602,0.6405198421907635,0.8373172429798097,0.8855883035507078,0.9357159433743328,0.6405198421907635,0.6405198421907635,0.2791057476599365,0.8373172429798097,0.1771176607101415,0.8855883035507078,0.09357159433743327,0.9357159433743328,0.7479839170138551,0.7940163464161489,0.7506964079592602
|
14 |
+
1,200,0.6419122766303087,0.8377813877929914,0.8846600139243443,0.9373404502204687,0.6419122766303087,0.6419122766303087,0.2792604625976638,0.8377813877929914,0.1769320027848689,0.8846600139243443,0.09373404502204688,0.9373404502204687,0.7486390611013503,0.7948583190190148,0.751245223305486,0.6419122766303087,0.8377813877929914,0.8846600139243443,0.9373404502204687,0.6419122766303087,0.6419122766303087,0.2792604625976638,0.8377813877929914,0.1769320027848689,0.8846600139243443,0.09373404502204688,0.9373404502204687,0.7486390611013503,0.7948583190190148,0.751245223305486
|
15 |
+
1,250,0.6407519145973544,0.8380134601995822,0.8841958691111627,0.9375725226270596,0.6407519145973544,0.6407519145973544,0.2793378200665274,0.8380134601995822,0.17683917382223252,0.8841958691111627,0.09375725226270597,0.9375725226270596,0.7475695940943103,0.7940846120553835,0.7501616220386313,0.6407519145973544,0.8380134601995822,0.8841958691111627,0.9375725226270596,0.6407519145973544,0.6407519145973544,0.2793378200665274,0.8380134601995822,0.17683917382223252,0.8841958691111627,0.09375725226270597,0.9375725226270596,0.7475695940943103,0.7940846120553835,0.7501616220386313
|
16 |
+
1,300,0.6453933627291715,0.8396379670457182,0.886980737990253,0.9389649570666048,0.6453933627291715,0.6453933627291715,0.27987932234857277,0.8396379670457182,0.17739614759805059,0.886980737990253,0.09389649570666048,0.9389649570666048,0.7510752688172047,0.7970899595138342,0.7536322354844067,0.6453933627291715,0.8396379670457182,0.886980737990253,0.9389649570666048,0.6453933627291715,0.6453933627291715,0.27987932234857277,0.8396379670457182,0.17739614759805059,0.886980737990253,0.09389649570666048,0.9389649570666048,0.7510752688172047,0.7970899595138342,0.7536322354844067
|
17 |
+
1,350,0.6433047110698538,0.8389417498259457,0.8862845207704804,0.9382687398468322,0.6433047110698538,0.6433047110698538,0.2796472499419819,0.8389417498259457,0.17725690415409606,0.8862845207704804,0.09382687398468322,0.9382687398468322,0.7496077792144171,0.7958106116451901,0.7521595058106199,0.6433047110698538,0.8389417498259457,0.8862845207704804,0.9382687398468322,0.6433047110698538,0.6433047110698538,0.2796472499419819,0.8389417498259457,0.17725690415409606,0.8862845207704804,0.09382687398468322,0.9382687398468322,0.7496077792144171,0.7958106116451901,0.7521595058106199
|
18 |
+
1,400,0.6421443490368995,0.8391738222325366,0.8848920863309353,0.9380366674402414,0.6421443490368995,0.6421443490368995,0.2797246074108455,0.8391738222325366,0.17697841726618702,0.8848920863309353,0.09380366674402413,0.9380366674402414,0.7485854634264945,0.7949598272426676,0.751152215928798,0.6421443490368995,0.8391738222325366,0.8848920863309353,0.9380366674402414,0.6421443490368995,0.6421443490368995,0.2797246074108455,0.8391738222325366,0.17697841726618702,0.8848920863309353,0.09380366674402413,0.9380366674402414,0.7485854634264945,0.7949598272426676,0.751152215928798
|
19 |
+
1,-1,0.6423764214434904,0.838477605012764,0.8846600139243443,0.9380366674402414,0.6423764214434904,0.6423764214434904,0.2794925350042546,0.838477605012764,0.17693200278486887,0.8846600139243443,0.09380366674402413,0.9380366674402414,0.748625984005423,0.7949800369626678,0.7511926295273631,0.6423764214434904,0.838477605012764,0.8846600139243443,0.9380366674402414,0.6423764214434904,0.6423764214434904,0.2794925350042546,0.838477605012764,0.17693200278486887,0.8846600139243443,0.09380366674402413,0.9380366674402414,0.748625984005423,0.7949800369626678,0.7511926295273631
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0459c9c26aedb8b7475f9cefcee3062288b1d3f2e5b6159a73d7271856fc33f
|
3 |
+
size 437951328
|
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": 512,
|
3 |
+
"do_lower_case": true
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"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 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|