Upload 11 files
Browse files- 1_Pooling/config.json +7 -0
- README.md +194 -0
- config.json +27 -0
- config_sentence_transformers.json +36 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -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": 312,
|
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
CHANGED
@@ -1,3 +1,197 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: mit
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- ru
|
4 |
+
- en
|
5 |
+
|
6 |
+
pipeline_tag: sentence-similarity
|
7 |
+
|
8 |
+
tags:
|
9 |
+
- russian
|
10 |
+
- pretraining
|
11 |
+
- embeddings
|
12 |
+
- tiny
|
13 |
+
- feature-extraction
|
14 |
+
- sentence-similarity
|
15 |
+
- sentence-transformers
|
16 |
+
- transformers
|
17 |
+
|
18 |
+
datasets:
|
19 |
+
- IlyaGusev/gazeta
|
20 |
+
- zloelias/lenta-ru
|
21 |
+
- HuggingFaceFW/fineweb-2
|
22 |
+
- HuggingFaceFW/fineweb
|
23 |
+
|
24 |
license: mit
|
25 |
+
base_model: sergeyzh/rubert-mini-sts
|
26 |
+
|
27 |
---
|
28 |
+
|
29 |
+
## rubert-mini-frida - лёгкая и быстрая модификация FRIDA
|
30 |
+
|
31 |
+
Модель для расчетов эмбеддингов предложений на русском и английском языках получена методом дистилляции эмбеддингов [ai-forever/FRIDA](https://huggingface.co/ai-forever/FRIDA) (размер эмбеддингов - 1536, слоёв - 24) в [sergeyzh/rubert-mini-sts](https://huggingface.co/sergeyzh/rubert-mini-sts) (размер эмбеддингов - 312, слоёв - 7). Основной режим использования FRIDA - CLS pooling заменен на mean pooling. Каких-либо других изменений поведения модели (модификации или фильтрации эмбеддингов, использования дополнительной модели) не производилось. Дистиляция выполнена в максимально возможном объеме - эмбеддинги русских и английских предложений, работа префиксов.
|
32 |
+
|
33 |
+
Рекомендуемый размер контекста модели соответствует FRIDA и не превышает 512 токенов (фактический унаследованный от исходной модели - 2048).
|
34 |
+
|
35 |
+
## Префиксы
|
36 |
+
Все префиксы унаследованы от FRIDA.
|
37 |
+
Оптимальный (обеспечивающий средние результаты) для большинства задач - "categorize: " прописан по умолчанию в [config_sentence_transformers.json](https://huggingface.co/sergeyzh/rubert-mini-frida/config_sentence_transformers.json)
|
38 |
+
|
39 |
+
Перечень используемых префиксов и их влияние на оценки модели в [encodechka](https://github.com/avidale/encodechka):
|
40 |
+
|
41 |
+
| Префикс | STS | PI | NLI | SA | TI |
|
42 |
+
|:-----------------------|:---------:|:---------:|:---------:|:---------:|:---------:|
|
43 |
+
| - | 0.839 | 0.762 | 0.475 | 0.801 | 0.972 |
|
44 |
+
| search_query: | 0.846 | 0.761 | 0.498 | 0.800 | 0.973 |
|
45 |
+
| search_document: | 0.830 | 0.748 | 0.468 | 0.794 | 0.972 |
|
46 |
+
| paraphrase: | 0.835 | **0.764** | 0.475 | 0.799 | 0.973 |
|
47 |
+
| categorize: | **0.850** | 0.761 | 0.516 | 0.802 | **0.973** |
|
48 |
+
| categorize_sentiment: | 0.755 | 0.656 | 0.427 | 0.798 | 0.959 |
|
49 |
+
| categorize_topic: | 0.734 | 0.523 | 0.389 | 0.728 | 0.959 |
|
50 |
+
| categorize_entailment: | 0.837 | 0.753 | **0.544** | **0.802** | 0.970 |
|
51 |
+
|
52 |
+
|
53 |
+
**Задачи:**
|
54 |
+
|
55 |
+
- Semantic text similarity (**STS**);
|
56 |
+
- Paraphrase identification (**PI**);
|
57 |
+
- Natural language inference (**NLI**);
|
58 |
+
- Sentiment analysis (**SA**);
|
59 |
+
- Toxicity identification (**TI**).
|
60 |
+
|
61 |
+
# Метрики
|
62 |
+
Оценки модели на бенчмарке [ruMTEB](https://habr.com/ru/companies/sberdevices/articles/831150/):
|
63 |
+
|
64 |
+
|Model Name | Metric | Frida | rubert-mini-frida | multilingual-e5-large-instruct | multilingual-e5-large |
|
65 |
+
|:----------------------------------|:--------------------|-----------------------:|--------------------:|---------------------:|----------------------:|
|
66 |
+
|CEDRClassification | Accuracy | **0.646** | 0.552 | 0.500 | 0.448 |
|
67 |
+
|GeoreviewClassification | Accuracy | **0.577** | 0.464 | 0.559 | 0.497 |
|
68 |
+
|GeoreviewClusteringP2P | V-measure | **0.783** | 0.698 | 0.743 | 0.605 |
|
69 |
+
|HeadlineClassification | Accuracy | **0.890** | 0.880 | 0.862 | 0.758 |
|
70 |
+
|InappropriatenessClassification | Accuracy | **0.783** | 0.698 | 0.655 | 0.616 |
|
71 |
+
|KinopoiskClassification | Accuracy | **0.705** | 0.595 | 0.661 | 0.566 |
|
72 |
+
|RiaNewsRetrieval | NDCG@10 | **0.868** | 0.721 | 0.824 | 0.807 |
|
73 |
+
|RuBQReranking | MAP@10 | **0.771** | 0.711 | 0.717 | 0.756 |
|
74 |
+
|RuBQRetrieval | NDCG@10 | 0.724 | 0.654 | 0.692 | **0.741** |
|
75 |
+
|RuReviewsClassification | Accuracy | **0.751** | 0.658 | 0.686 | 0.653 |
|
76 |
+
|RuSTSBenchmarkSTS | Pearson correlation | 0.814 | 0.803 | **0.840** | 0.831 |
|
77 |
+
|RuSciBenchGRNTIClassification | Accuracy | **0.699** | 0.625 | 0.651 | 0.582 |
|
78 |
+
|RuSciBenchGRNTIClusteringP2P | V-measure | **0.670** | 0.586 | 0.622 | 0.520 |
|
79 |
+
|RuSciBenchOECDClassification | Accuracy | **0.546** | 0.493 | 0.502 | 0.445 |
|
80 |
+
|RuSciBenchOECDClusteringP2P | V-measure | **0.566** | 0.507 | 0.528 | 0.450 |
|
81 |
+
|SensitiveTopicsClassification | Accuracy | **0.398** | 0.373 | 0.323 | 0.257 |
|
82 |
+
|TERRaClassification | Average Precision | **0.665** | 0.606 | 0.639 | 0.584 |
|
83 |
+
|
84 |
+
|Model Name | Metric | Frida | rubert-mini-frida | multilingual-e5-large-instruct | multilingual-e5-large |
|
85 |
+
|:----------------------------------|:--------------------|-----------------------:|--------------------:|----------------------:|---------------------:|
|
86 |
+
|Classification | Accuracy | **0.707** | 0.631 | 0.654 | 0.588 |
|
87 |
+
|Clustering | V-measure | **0.673** | 0.597 | 0.631 | 0.525 |
|
88 |
+
|MultiLabelClassification | Accuracy | **0.522** | 0.463 | 0.412 | 0.353 |
|
89 |
+
|PairClassification | Average Precision | **0.665** | 0.606 | 0.639 | 0.584 |
|
90 |
+
|Reranking | MAP@10 | **0.771** | 0.711 | 0.717 | 0.756 |
|
91 |
+
|Retrieval | NDCG@10 | **0.796** | 0.687 | 0.758 | 0.774 |
|
92 |
+
|STS | Pearson correlation | 0.814 | 0.803 | **0.840** | 0.831 |
|
93 |
+
|Average | Average | **0.707** | 0.643 | 0.664 | 0.630 |
|
94 |
+
|
95 |
+
|
96 |
+
|
97 |
+
## Использование модели с библиотекой `transformers`:
|
98 |
+
|
99 |
+
```python
|
100 |
+
import torch
|
101 |
+
import torch.nn.functional as F
|
102 |
+
from transformers import AutoTokenizer, AutoModel
|
103 |
+
|
104 |
+
|
105 |
+
def pool(hidden_state, mask, pooling_method="mean"):
|
106 |
+
if pooling_method == "mean":
|
107 |
+
s = torch.sum(hidden_state * mask.unsqueeze(-1).float(), dim=1)
|
108 |
+
d = mask.sum(axis=1, keepdim=True).float()
|
109 |
+
return s / d
|
110 |
+
elif pooling_method == "cls":
|
111 |
+
return hidden_state[:, 0]
|
112 |
+
|
113 |
+
inputs = [
|
114 |
+
#
|
115 |
+
"paraphrase: В Ярославской области разрешили работу бань, но без посетителей",
|
116 |
+
"categorize_entailment: Женщину доставили в больницу, за ее жизнь сейчас борются врачи.",
|
117 |
+
"search_query: Сколько программистов нужно, чтобы вкрутить лампочку?",
|
118 |
+
#
|
119 |
+
"paraphrase: Ярославским баням разрешили работать без посетителей",
|
120 |
+
"categorize_entailment: Женщину спасают врачи.",
|
121 |
+
"search_document: Чтобы вкрутить лампочку, требуется три программиста: один напишет программу извлечения лампочки, другой — вкручивания лампочки, а третий проведет тестирование."
|
122 |
+
]
|
123 |
+
|
124 |
+
tokenizer = AutoTokenizer.from_pretrained("sergeyzh/rubert-mini-frida")
|
125 |
+
model = AutoModel.from_pretrained("sergeyzh/rubert-mini-frida")
|
126 |
+
|
127 |
+
tokenized_inputs = tokenizer(inputs, max_length=512, padding=True, truncation=True, return_tensors="pt")
|
128 |
+
|
129 |
+
with torch.no_grad():
|
130 |
+
outputs = model(**tokenized_inputs)
|
131 |
+
|
132 |
+
embeddings = pool(
|
133 |
+
outputs.last_hidden_state,
|
134 |
+
tokenized_inputs["attention_mask"],
|
135 |
+
pooling_method="mean"
|
136 |
+
)
|
137 |
+
|
138 |
+
embeddings = F.normalize(embeddings, p=2, dim=1)
|
139 |
+
sim_scores = embeddings[:3] @ embeddings[3:].T
|
140 |
+
print(sim_scores.diag().tolist())
|
141 |
+
# [0.9423348903656006, 0.8306248188018799, 0.7095720767974854]
|
142 |
+
# [0.9360030293464661, 0.8591322302818298, 0.728583037853241] - FRIDA
|
143 |
+
```
|
144 |
+
|
145 |
+
## Использование с `sentence_transformers`:
|
146 |
+
|
147 |
+
```python
|
148 |
+
from sentence_transformers import SentenceTransformer
|
149 |
+
|
150 |
+
inputs = [
|
151 |
+
#
|
152 |
+
"paraphrase: В Ярославской области разрешили работу бань, но без посетителей",
|
153 |
+
"categorize_entailment: Женщину доставили в больницу, за ее жизнь сейчас борются врачи.",
|
154 |
+
"search_query: Сколько программистов нужно, чтобы вкрутить лампочку?",
|
155 |
+
#
|
156 |
+
"paraphrase: Ярославским баням разрешили работать без посетителей",
|
157 |
+
"categorize_entailment: Женщину спасают врачи.",
|
158 |
+
"search_document: Чтобы вкрутить лампочку, требуется три программиста: один напишет программу извлечения лампочки, другой — вкручивания лампочки, а третий проведет тестирование."
|
159 |
+
]
|
160 |
+
|
161 |
+
# loads model with mean pooling
|
162 |
+
model = SentenceTransformer("sergeyzh/rubert-mini-frida")
|
163 |
+
|
164 |
+
# embeddings are normalized by default
|
165 |
+
embeddings = model.encode(inputs, convert_to_tensor=True)
|
166 |
+
|
167 |
+
sim_scores = embeddings[:3] @ embeddings[3:].T
|
168 |
+
print(sim_scores.diag().tolist())
|
169 |
+
# [0.9413310289382935, 0.8383190631866455, 0.7195918560028076]
|
170 |
+
# [0.9360026717185974, 0.8591331243515015, 0.7285830974578857] - FRIDA
|
171 |
+
```
|
172 |
+
|
173 |
+
### рекомендуемый с использованием prompt (sentence-transformers>=2.4.0):
|
174 |
+
|
175 |
+
```python
|
176 |
+
from sentence_transformers import SentenceTransformer
|
177 |
+
|
178 |
+
# loads model with mean pooling
|
179 |
+
model = SentenceTransformer("sergeyzh/rubert-mini-frida")
|
180 |
+
|
181 |
+
paraphrase = model.encode(["В Ярославской области разрешили работу бань, но без посетителей", "Ярославским баням разрешили работать без посетителей"], prompt="paraphrase: ")
|
182 |
+
print(paraphrase[0] @ paraphrase[1].T)
|
183 |
+
# 0.94233495
|
184 |
+
# 0.9360032 - FRIDA
|
185 |
+
|
186 |
+
categorize_entailment = model.encode(["Женщину доставили в больницу, за ее жизнь сейчас борются врачи.", "Женщину спасают врачи."], prompt="categorize_entailment: ")
|
187 |
+
print(categorize_entailment[0] @ categorize_entailment[1].T)
|
188 |
+
# 0.8306249
|
189 |
+
# 0.8591322 - FRIDA
|
190 |
+
|
191 |
+
query_embedding = model.encode("Сколько программистов нужно, чтобы вкрутить лампочку?", prompt="search_query: ")
|
192 |
+
document_embedding = model.encode("Чтобы вкрутить лампочку, требуется три программиста: один напишет программу извлечения лампочки, другой — вкручивания лампочки, а третий проведет тестирование.", prompt="search_document: ")
|
193 |
+
print(query_embedding @ document_embedding.T)
|
194 |
+
# 0.70957196
|
195 |
+
# 0.7285831 - FRIDA
|
196 |
+
```
|
197 |
+
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sergeyzh/rubert-mini-frida",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_size": 312,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 312,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 600,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 2048,
|
17 |
+
"model_type": "bert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 7,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.48.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 83828
|
27 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.7.0",
|
4 |
+
"transformers": "4.40.1",
|
5 |
+
"pytorch": "2.2.1+cu118"
|
6 |
+
},
|
7 |
+
"prompts": {
|
8 |
+
"query": "search_query: ",
|
9 |
+
"passage": "search_document: ",
|
10 |
+
"CEDRClassification": "categorize_sentiment: ",
|
11 |
+
"GeoreviewClassification": "categorize_entailment: ",
|
12 |
+
"GeoreviewClusteringP2P": "paraphrase: ",
|
13 |
+
"HeadlineClassification": "categorize_topic: ",
|
14 |
+
"InappropriatenessClassification": "categorize_topic: ",
|
15 |
+
"KinopoiskClassification": "categorize_sentiment: ",
|
16 |
+
"MassiveIntentClassification": "categorize_entailment: ",
|
17 |
+
"MassiveScenarioClassification": "categorize_entailment: ",
|
18 |
+
"RuReviewsClassification": "categorize_entailment: ",
|
19 |
+
"RUParaPhraserSTS": "paraphrase: ",
|
20 |
+
"RuSTSBenchmarkSTS": "search_query: ",
|
21 |
+
"STS22": "paraphrase: ",
|
22 |
+
"RuSciBenchGRNTIClassification": "categorize_topic: ",
|
23 |
+
"RuSciBenchGRNTIClusteringP2P": "categorize_topic: ",
|
24 |
+
"RuSciBenchOECDClassification": "categorize_topic: ",
|
25 |
+
"RuSciBenchOECDClusteringP2P": "categorize_topic: ",
|
26 |
+
"SensitiveTopicsClassification": "categorize_topic: ",
|
27 |
+
"TERRa": "categorize_entailment: ",
|
28 |
+
"Classification": "categorize: ",
|
29 |
+
"MultilabelClassification": "categorize: ",
|
30 |
+
"Clustering": "categorize: ",
|
31 |
+
"PairClassification": "categorize: ",
|
32 |
+
"STS": "paraphrase: "
|
33 |
+
},
|
34 |
+
"default_prompt_name": "Classification",
|
35 |
+
"similarity_fn_name": null
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f7f7e9866e57e7f19f76d3960373177f30c6ac627a8c6a677472d526f44d1cd
|
3 |
+
size 129063328
|
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": 2048,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 2048,
|
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
|
|