Push model using huggingface_hub.
Browse files- 1_Pooling/config.json +10 -0
- README.md +393 -0
- config.json +29 -0
- config_sentence_transformers.json +10 -0
- config_setfit.json +4 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +66 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,393 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mini1013/master_domain
|
| 3 |
+
library_name: setfit
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
pipeline_tag: text-classification
|
| 7 |
+
tags:
|
| 8 |
+
- setfit
|
| 9 |
+
- sentence-transformers
|
| 10 |
+
- text-classification
|
| 11 |
+
- generated_from_setfit_trainer
|
| 12 |
+
widget:
|
| 13 |
+
- text: '[라네즈] [체리 블러썸] 워터슬리핑마스크 EX 70ml 상세 설명 참조 (#M)쿠팡 홈>뷰티>스킨케어>마스크/팩>슬리핑팩 Coupang
|
| 14 |
+
> 뷰티 > 스킨케어 > 마스크/팩 > 슬리핑팩'
|
| 15 |
+
- text: 메디힐 티트리 케어솔루션 에센셜 마스크 이엑스 LotteOn > 뷰티 > 마스크/팩 > 마스크팩 LotteOn > 뷰티 > 마스크/팩
|
| 16 |
+
> 마스크팩
|
| 17 |
+
- text: 이니스프리 블랙티 유스 인핸싱 앰플 마스크 28ml 1개입 × 5개 LotteOn > 뷰티 > 스킨케어 > 마스크/팩 > 마스크팩 LotteOn
|
| 18 |
+
> 뷰티 > 스킨케어 > 마스크/팩 > 마스크팩
|
| 19 |
+
- text: 메디힐 마스크팩 티트리 수분 보습 진정 트러블 30. 메디힐 M.E.N 타임톡스_[1장] 홈>메디힐;홈>스킨케어>마스크팩;(#M)홈>화장품/미용>마스크/팩>마스크시트
|
| 20 |
+
Naverstore > 화장품/미용 > 마스크/팩 > 마스크시트
|
| 21 |
+
- text: 이니스프리 블랙티 유스 인핸싱 앰플 마스크 28ml 1개입 × 5개 LotteOn > 뷰티 > 스킨케어 > 스킨/토너 LotteOn
|
| 22 |
+
> 뷰티 > 스킨케어 > 스킨/토너
|
| 23 |
+
inference: true
|
| 24 |
+
model-index:
|
| 25 |
+
- name: SetFit with mini1013/master_domain
|
| 26 |
+
results:
|
| 27 |
+
- task:
|
| 28 |
+
type: text-classification
|
| 29 |
+
name: Text Classification
|
| 30 |
+
dataset:
|
| 31 |
+
name: Unknown
|
| 32 |
+
type: unknown
|
| 33 |
+
split: test
|
| 34 |
+
metrics:
|
| 35 |
+
- type: accuracy
|
| 36 |
+
value: 0.5683229813664596
|
| 37 |
+
name: Accuracy
|
| 38 |
+
---
|
| 39 |
+
|
| 40 |
+
# SetFit with mini1013/master_domain
|
| 41 |
+
|
| 42 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [mini1013/master_domain](https://huggingface.co/mini1013/master_domain) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
| 43 |
+
|
| 44 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
| 45 |
+
|
| 46 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
| 47 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
| 48 |
+
|
| 49 |
+
## Model Details
|
| 50 |
+
|
| 51 |
+
### Model Description
|
| 52 |
+
- **Model Type:** SetFit
|
| 53 |
+
- **Sentence Transformer body:** [mini1013/master_domain](https://huggingface.co/mini1013/master_domain)
|
| 54 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
| 55 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 56 |
+
- **Number of Classes:** 4 classes
|
| 57 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 58 |
+
<!-- - **Language:** Unknown -->
|
| 59 |
+
<!-- - **License:** Unknown -->
|
| 60 |
+
|
| 61 |
+
### Model Sources
|
| 62 |
+
|
| 63 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
| 64 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
| 65 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 66 |
+
|
| 67 |
+
### Model Labels
|
| 68 |
+
| Label | Examples |
|
| 69 |
+
|:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 70 |
+
| 3 | <ul><li>'[묶음할인~25%+T11%]에뛰드 타임어택 ~60% 전품목 빅세일/호랑이의 해 무직타이거 콜라보 런칭 50.패치(1)_매끈반짝3단코팩5개_650000010398 쇼킹딜 홈>뷰티>선케어/메이크업>아이메이크업;11st>메이크업>아이메이크업>아이섀도우;11st>뷰티>선케어/메이크업>아이메이크업;11st Hour Event > 패션/뷰티 > 뷰티 > 선케어/메이크업 > 아이메이크업 11st Hour Event > 패션/뷰티 > 뷰티 > 선케어/메이크업 > 아이메이크업'</li><li>'차앤박 안티포어 블랙헤드 클리어 키트 스트립 (#M)홈>화장품/미용>마스크/팩>코팩 Naverstore > 화장품/미용 > 마스크/팩 > 코팩'</li><li>'[차앤박] CNP 안티포어 블랙헤드 클리어 키트 스트립 3세트(3회분) (#M)위메프 > 뷰티 > 스킨케어 > 팩/마스크 > 코팩 위메프 > 뷰티 > 스킨케어 > 팩/마스크 > 코팩'</li></ul> |
|
| 71 |
+
| 0 | <ul><li>'[10%+15%]한스킨 6월 클리어런스 클렌징오일/토너패드/에센스/블랙헤드/마스크~81%OF 블레미쉬 커버 컨실러_브라이트 [GH990355] 쇼킹딜 홈>뷰티>선케어/메이크업>페이스메이크업;11st>뷰티>선케어/메이크업>페이스메이크업;11st>메이크업>페이스메이크업>BB크림;11st > 뷰티 > 메이크업 > 페이스메이크업 11st Hour Event > 패션/뷰티 > 뷰티 > 선케어/메이크업 > 페이스메이크업'</li><li>'네이처리퍼블릭 [네이처리퍼블릭][1+1]수딩 앤 모이스처 알로에베라 수딩젤 마스크시트 단일옵션 × 선택완료 쿠팡 홈>뷰티>스킨케어>마스크/팩>코팩/기타패치>기타패치;Coupang > 뷰티 > 로드샵 > 스킨케어 > 마스크/팩 > 코팩/기타패치 > 기타패치;(#M)쿠팡 홈>뷰티>스킨케어>마스크/팩>패치/코팩>기타패치 Coupang > 뷰티 > 스킨케어 > 마스크/팩 > 패치/코팩 > 기타패치'</li><li>'이니스프리 블랙티 유스 인핸싱 앰플 마스크 28ml 1개입 × 5개 LotteOn > 뷰티 > 스킨케어 > 마스크/팩 > 마스크팩 LotteOn > 뷰티 > 스킨케어 > 마스크/팩 > 마스크팩'</li></ul> |
|
| 72 |
+
| 2 | <ul><li>'[쿠폰30%+스토어10%]에뛰드 ~64% 21년 신제품 앵콜전(플레이컬러아이즈/그림자쉐딩/픽싱틴트/순정) 58.AC 클린업_핑크마스크_111080503 쇼킹딜 홈>뷰티>스킨케어>크림;쇼킹딜 홈>뷰티>스킨케어>스킨/로션;11st>스킨케어>스킨/토너>스킨/토너;11st>메이크업>아이메이크업>아이섀도우;쇼킹딜 홈>뷰티>선케어/메이크업>아이메이크업;11st>뷰티>선케어/메이크업>아이메이크업;11st > timedeal 11st Hour Event > 패션/뷰티 > 뷰티 > 선케어/메이크업 > 아이메이크업'</li><li>'마스크 오브 매그너민티 315g 파워 마스크 (#M)뷰티>헤어/바디/미용기기>헤어케어>기획세트 CJmall > 뷰티 > 헤어/바디/미용기기 > 헤어스타일링 > 왁스/스프레이'</li><li>'[말썽피부케어추천] 쑥뜸팩+쑥카밍젤 (#M)위메프 > 뷰티 > 클렌징/필링 > 필링젤/스크럽 > 필링젤/스크럽 위메프 > 뷰티 > 클렌징/필링 > 필링젤/스크럽 > 필링젤/스크럽'</li></ul> |
|
| 73 |
+
| 1 | <ul><li>'티르티르 물광 콜라겐 生생크림 버블팩 물광마스크 노워시 80ml 당일출고 티르티르콜라겐80ml (#M)홈>화장품/미용>스킨케어>크림 Naverstore > 화장품/미용 > 스킨케어 > 크림'</li><li>"달바 모델 한혜진's pick 화이트트러플 세럼 7통+아이크림1통 단일상품 TV쇼핑>TV쇼핑 화장품/이미용>화장품/향수>기초스킨케어;(#M)TV상품>TV쇼핑 화장품/이미용>화장품/향수>기초스킨케어 CJmall > 뷰티 > 화장품/향수 > 더모코스메틱 > 에센스/세럼/오일"</li><li>'시슬리 벨벳 슬리핑 마스크 LotteOn > 뷰티 > 남성화장품 > 남성화장품세트 LotteOn > 뷰티 > 남성화장품 > 남성화장품세트'</li></ul> |
|
| 74 |
+
|
| 75 |
+
## Evaluation
|
| 76 |
+
|
| 77 |
+
### Metrics
|
| 78 |
+
| Label | Accuracy |
|
| 79 |
+
|:--------|:---------|
|
| 80 |
+
| **all** | 0.5683 |
|
| 81 |
+
|
| 82 |
+
## Uses
|
| 83 |
+
|
| 84 |
+
### Direct Use for Inference
|
| 85 |
+
|
| 86 |
+
First install the SetFit library:
|
| 87 |
+
|
| 88 |
+
```bash
|
| 89 |
+
pip install setfit
|
| 90 |
+
```
|
| 91 |
+
|
| 92 |
+
Then you can load this model and run inference.
|
| 93 |
+
|
| 94 |
+
```python
|
| 95 |
+
from setfit import SetFitModel
|
| 96 |
+
|
| 97 |
+
# Download from the 🤗 Hub
|
| 98 |
+
model = SetFitModel.from_pretrained("mini1013/master_cate_bt_top3_test")
|
| 99 |
+
# Run inference
|
| 100 |
+
preds = model("메디힐 티트리 케어솔루션 에센셜 마스크 이엑스 LotteOn > 뷰티 > 마스크/팩 > 마스크팩 LotteOn > 뷰티 > 마스크/팩 > 마스크팩")
|
| 101 |
+
```
|
| 102 |
+
|
| 103 |
+
<!--
|
| 104 |
+
### Downstream Use
|
| 105 |
+
|
| 106 |
+
*List how someone could finetune this model on their own dataset.*
|
| 107 |
+
-->
|
| 108 |
+
|
| 109 |
+
<!--
|
| 110 |
+
### Out-of-Scope Use
|
| 111 |
+
|
| 112 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 113 |
+
-->
|
| 114 |
+
|
| 115 |
+
<!--
|
| 116 |
+
## Bias, Risks and Limitations
|
| 117 |
+
|
| 118 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 119 |
+
-->
|
| 120 |
+
|
| 121 |
+
<!--
|
| 122 |
+
### Recommendations
|
| 123 |
+
|
| 124 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 125 |
+
-->
|
| 126 |
+
|
| 127 |
+
## Training Details
|
| 128 |
+
|
| 129 |
+
### Training Set Metrics
|
| 130 |
+
| Training set | Min | Median | Max |
|
| 131 |
+
|:-------------|:----|:-------|:----|
|
| 132 |
+
| Word count | 12 | 22.655 | 91 |
|
| 133 |
+
|
| 134 |
+
| Label | Training Sample Count |
|
| 135 |
+
|:------|:----------------------|
|
| 136 |
+
| 0 | 50 |
|
| 137 |
+
| 1 | 50 |
|
| 138 |
+
| 2 | 50 |
|
| 139 |
+
| 3 | 50 |
|
| 140 |
+
|
| 141 |
+
### Training Hyperparameters
|
| 142 |
+
- batch_size: (64, 64)
|
| 143 |
+
- num_epochs: (30, 30)
|
| 144 |
+
- max_steps: -1
|
| 145 |
+
- sampling_strategy: oversampling
|
| 146 |
+
- num_iterations: 100
|
| 147 |
+
- body_learning_rate: (2e-05, 1e-05)
|
| 148 |
+
- head_learning_rate: 0.01
|
| 149 |
+
- loss: CosineSimilarityLoss
|
| 150 |
+
- distance_metric: cosine_distance
|
| 151 |
+
- margin: 0.25
|
| 152 |
+
- end_to_end: False
|
| 153 |
+
- use_amp: False
|
| 154 |
+
- warmup_proportion: 0.1
|
| 155 |
+
- l2_weight: 0.01
|
| 156 |
+
- seed: 42
|
| 157 |
+
- eval_max_steps: -1
|
| 158 |
+
- load_best_model_at_end: False
|
| 159 |
+
|
| 160 |
+
### Training Results
|
| 161 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
| 162 |
+
|:-------:|:----:|:-------------:|:---------------:|
|
| 163 |
+
| 0.0032 | 1 | 0.478 | - |
|
| 164 |
+
| 0.1597 | 50 | 0.4392 | - |
|
| 165 |
+
| 0.3195 | 100 | 0.4128 | - |
|
| 166 |
+
| 0.4792 | 150 | 0.3767 | - |
|
| 167 |
+
| 0.6390 | 200 | 0.3406 | - |
|
| 168 |
+
| 0.7987 | 250 | 0.2889 | - |
|
| 169 |
+
| 0.9585 | 300 | 0.2482 | - |
|
| 170 |
+
| 1.1182 | 350 | 0.2336 | - |
|
| 171 |
+
| 1.2780 | 400 | 0.1948 | - |
|
| 172 |
+
| 1.4377 | 450 | 0.1284 | - |
|
| 173 |
+
| 1.5974 | 500 | 0.0958 | - |
|
| 174 |
+
| 1.7572 | 550 | 0.0893 | - |
|
| 175 |
+
| 1.9169 | 600 | 0.0788 | - |
|
| 176 |
+
| 2.0767 | 650 | 0.0706 | - |
|
| 177 |
+
| 2.2364 | 700 | 0.058 | - |
|
| 178 |
+
| 2.3962 | 750 | 0.0476 | - |
|
| 179 |
+
| 2.5559 | 800 | 0.0406 | - |
|
| 180 |
+
| 2.7157 | 850 | 0.0327 | - |
|
| 181 |
+
| 2.8754 | 900 | 0.0198 | - |
|
| 182 |
+
| 3.0351 | 950 | 0.0183 | - |
|
| 183 |
+
| 3.1949 | 1000 | 0.0131 | - |
|
| 184 |
+
| 3.3546 | 1050 | 0.0093 | - |
|
| 185 |
+
| 3.5144 | 1100 | 0.005 | - |
|
| 186 |
+
| 3.6741 | 1150 | 0.0004 | - |
|
| 187 |
+
| 3.8339 | 1200 | 0.0001 | - |
|
| 188 |
+
| 3.9936 | 1250 | 0.0001 | - |
|
| 189 |
+
| 4.1534 | 1300 | 0.0 | - |
|
| 190 |
+
| 4.3131 | 1350 | 0.0001 | - |
|
| 191 |
+
| 4.4728 | 1400 | 0.0 | - |
|
| 192 |
+
| 4.6326 | 1450 | 0.0 | - |
|
| 193 |
+
| 4.7923 | 1500 | 0.0 | - |
|
| 194 |
+
| 4.9521 | 1550 | 0.0 | - |
|
| 195 |
+
| 5.1118 | 1600 | 0.0 | - |
|
| 196 |
+
| 5.2716 | 1650 | 0.0006 | - |
|
| 197 |
+
| 5.4313 | 1700 | 0.0001 | - |
|
| 198 |
+
| 5.5911 | 1750 | 0.0 | - |
|
| 199 |
+
| 5.7508 | 1800 | 0.0 | - |
|
| 200 |
+
| 5.9105 | 1850 | 0.0 | - |
|
| 201 |
+
| 6.0703 | 1900 | 0.0 | - |
|
| 202 |
+
| 6.2300 | 1950 | 0.0 | - |
|
| 203 |
+
| 6.3898 | 2000 | 0.0 | - |
|
| 204 |
+
| 6.5495 | 2050 | 0.0 | - |
|
| 205 |
+
| 6.7093 | 2100 | 0.0 | - |
|
| 206 |
+
| 6.8690 | 2150 | 0.0 | - |
|
| 207 |
+
| 7.0288 | 2200 | 0.0 | - |
|
| 208 |
+
| 7.1885 | 2250 | 0.0 | - |
|
| 209 |
+
| 7.3482 | 2300 | 0.0 | - |
|
| 210 |
+
| 7.5080 | 2350 | 0.0 | - |
|
| 211 |
+
| 7.6677 | 2400 | 0.0 | - |
|
| 212 |
+
| 7.8275 | 2450 | 0.0 | - |
|
| 213 |
+
| 7.9872 | 2500 | 0.0 | - |
|
| 214 |
+
| 8.1470 | 2550 | 0.0 | - |
|
| 215 |
+
| 8.3067 | 2600 | 0.0002 | - |
|
| 216 |
+
| 8.4665 | 2650 | 0.0 | - |
|
| 217 |
+
| 8.6262 | 2700 | 0.0 | - |
|
| 218 |
+
| 8.7859 | 2750 | 0.0001 | - |
|
| 219 |
+
| 8.9457 | 2800 | 0.0 | - |
|
| 220 |
+
| 9.1054 | 2850 | 0.0 | - |
|
| 221 |
+
| 9.2652 | 2900 | 0.0 | - |
|
| 222 |
+
| 9.4249 | 2950 | 0.0002 | - |
|
| 223 |
+
| 9.5847 | 3000 | 0.0096 | - |
|
| 224 |
+
| 9.7444 | 3050 | 0.0007 | - |
|
| 225 |
+
| 9.9042 | 3100 | 0.0006 | - |
|
| 226 |
+
| 10.0639 | 3150 | 0.0005 | - |
|
| 227 |
+
| 10.2236 | 3200 | 0.0001 | - |
|
| 228 |
+
| 10.3834 | 3250 | 0.0018 | - |
|
| 229 |
+
| 10.5431 | 3300 | 0.0003 | - |
|
| 230 |
+
| 10.7029 | 3350 | 0.0003 | - |
|
| 231 |
+
| 10.8626 | 3400 | 0.0 | - |
|
| 232 |
+
| 11.0224 | 3450 | 0.0016 | - |
|
| 233 |
+
| 11.1821 | 3500 | 0.0058 | - |
|
| 234 |
+
| 11.3419 | 3550 | 0.0055 | - |
|
| 235 |
+
| 11.5016 | 3600 | 0.005 | - |
|
| 236 |
+
| 11.6613 | 3650 | 0.0062 | - |
|
| 237 |
+
| 11.8211 | 3700 | 0.0017 | - |
|
| 238 |
+
| 11.9808 | 3750 | 0.0002 | - |
|
| 239 |
+
| 12.1406 | 3800 | 0.0001 | - |
|
| 240 |
+
| 12.3003 | 3850 | 0.0 | - |
|
| 241 |
+
| 12.4601 | 3900 | 0.0 | - |
|
| 242 |
+
| 12.6198 | 3950 | 0.0 | - |
|
| 243 |
+
| 12.7796 | 4000 | 0.0 | - |
|
| 244 |
+
| 12.9393 | 4050 | 0.0 | - |
|
| 245 |
+
| 13.0990 | 4100 | 0.0 | - |
|
| 246 |
+
| 13.2588 | 4150 | 0.0 | - |
|
| 247 |
+
| 13.4185 | 4200 | 0.0 | - |
|
| 248 |
+
| 13.5783 | 4250 | 0.0 | - |
|
| 249 |
+
| 13.7380 | 4300 | 0.0 | - |
|
| 250 |
+
| 13.8978 | 4350 | 0.0 | - |
|
| 251 |
+
| 14.0575 | 4400 | 0.0 | - |
|
| 252 |
+
| 14.2173 | 4450 | 0.0 | - |
|
| 253 |
+
| 14.3770 | 4500 | 0.0 | - |
|
| 254 |
+
| 14.5367 | 4550 | 0.0 | - |
|
| 255 |
+
| 14.6965 | 4600 | 0.0 | - |
|
| 256 |
+
| 14.8562 | 4650 | 0.0 | - |
|
| 257 |
+
| 15.0160 | 4700 | 0.0 | - |
|
| 258 |
+
| 15.1757 | 4750 | 0.0 | - |
|
| 259 |
+
| 15.3355 | 4800 | 0.0 | - |
|
| 260 |
+
| 15.4952 | 4850 | 0.0 | - |
|
| 261 |
+
| 15.6550 | 4900 | 0.0 | - |
|
| 262 |
+
| 15.8147 | 4950 | 0.0 | - |
|
| 263 |
+
| 15.9744 | 5000 | 0.0 | - |
|
| 264 |
+
| 16.1342 | 5050 | 0.0 | - |
|
| 265 |
+
| 16.2939 | 5100 | 0.0 | - |
|
| 266 |
+
| 16.4537 | 5150 | 0.0 | - |
|
| 267 |
+
| 16.6134 | 5200 | 0.0 | - |
|
| 268 |
+
| 16.7732 | 5250 | 0.0 | - |
|
| 269 |
+
| 16.9329 | 5300 | 0.0 | - |
|
| 270 |
+
| 17.0927 | 5350 | 0.0 | - |
|
| 271 |
+
| 17.2524 | 5400 | 0.0 | - |
|
| 272 |
+
| 17.4121 | 5450 | 0.0 | - |
|
| 273 |
+
| 17.5719 | 5500 | 0.0 | - |
|
| 274 |
+
| 17.7316 | 5550 | 0.0 | - |
|
| 275 |
+
| 17.8914 | 5600 | 0.0 | - |
|
| 276 |
+
| 18.0511 | 5650 | 0.0 | - |
|
| 277 |
+
| 18.2109 | 5700 | 0.0 | - |
|
| 278 |
+
| 18.3706 | 5750 | 0.0 | - |
|
| 279 |
+
| 18.5304 | 5800 | 0.0 | - |
|
| 280 |
+
| 18.6901 | 5850 | 0.0 | - |
|
| 281 |
+
| 18.8498 | 5900 | 0.0 | - |
|
| 282 |
+
| 19.0096 | 5950 | 0.0 | - |
|
| 283 |
+
| 19.1693 | 6000 | 0.0 | - |
|
| 284 |
+
| 19.3291 | 6050 | 0.0 | - |
|
| 285 |
+
| 19.4888 | 6100 | 0.0 | - |
|
| 286 |
+
| 19.6486 | 6150 | 0.0 | - |
|
| 287 |
+
| 19.8083 | 6200 | 0.0 | - |
|
| 288 |
+
| 19.9681 | 6250 | 0.0 | - |
|
| 289 |
+
| 20.1278 | 6300 | 0.0 | - |
|
| 290 |
+
| 20.2875 | 6350 | 0.0 | - |
|
| 291 |
+
| 20.4473 | 6400 | 0.0 | - |
|
| 292 |
+
| 20.6070 | 6450 | 0.0 | - |
|
| 293 |
+
| 20.7668 | 6500 | 0.0 | - |
|
| 294 |
+
| 20.9265 | 6550 | 0.0 | - |
|
| 295 |
+
| 21.0863 | 6600 | 0.0 | - |
|
| 296 |
+
| 21.2460 | 6650 | 0.0 | - |
|
| 297 |
+
| 21.4058 | 6700 | 0.0 | - |
|
| 298 |
+
| 21.5655 | 6750 | 0.0 | - |
|
| 299 |
+
| 21.7252 | 6800 | 0.0 | - |
|
| 300 |
+
| 21.8850 | 6850 | 0.0 | - |
|
| 301 |
+
| 22.0447 | 6900 | 0.0 | - |
|
| 302 |
+
| 22.2045 | 6950 | 0.0 | - |
|
| 303 |
+
| 22.3642 | 7000 | 0.0 | - |
|
| 304 |
+
| 22.5240 | 7050 | 0.0 | - |
|
| 305 |
+
| 22.6837 | 7100 | 0.0 | - |
|
| 306 |
+
| 22.8435 | 7150 | 0.0 | - |
|
| 307 |
+
| 23.0032 | 7200 | 0.0 | - |
|
| 308 |
+
| 23.1629 | 7250 | 0.0 | - |
|
| 309 |
+
| 23.3227 | 7300 | 0.0 | - |
|
| 310 |
+
| 23.4824 | 7350 | 0.0 | - |
|
| 311 |
+
| 23.6422 | 7400 | 0.0 | - |
|
| 312 |
+
| 23.8019 | 7450 | 0.0 | - |
|
| 313 |
+
| 23.9617 | 7500 | 0.0 | - |
|
| 314 |
+
| 24.1214 | 7550 | 0.0 | - |
|
| 315 |
+
| 24.2812 | 7600 | 0.0 | - |
|
| 316 |
+
| 24.4409 | 7650 | 0.0 | - |
|
| 317 |
+
| 24.6006 | 7700 | 0.0 | - |
|
| 318 |
+
| 24.7604 | 7750 | 0.0 | - |
|
| 319 |
+
| 24.9201 | 7800 | 0.0 | - |
|
| 320 |
+
| 25.0799 | 7850 | 0.0 | - |
|
| 321 |
+
| 25.2396 | 7900 | 0.0 | - |
|
| 322 |
+
| 25.3994 | 7950 | 0.0 | - |
|
| 323 |
+
| 25.5591 | 8000 | 0.0 | - |
|
| 324 |
+
| 25.7188 | 8050 | 0.0 | - |
|
| 325 |
+
| 25.8786 | 8100 | 0.0 | - |
|
| 326 |
+
| 26.0383 | 8150 | 0.0 | - |
|
| 327 |
+
| 26.1981 | 8200 | 0.0 | - |
|
| 328 |
+
| 26.3578 | 8250 | 0.0 | - |
|
| 329 |
+
| 26.5176 | 8300 | 0.0 | - |
|
| 330 |
+
| 26.6773 | 8350 | 0.0 | - |
|
| 331 |
+
| 26.8371 | 8400 | 0.0 | - |
|
| 332 |
+
| 26.9968 | 8450 | 0.0 | - |
|
| 333 |
+
| 27.1565 | 8500 | 0.0 | - |
|
| 334 |
+
| 27.3163 | 8550 | 0.0 | - |
|
| 335 |
+
| 27.4760 | 8600 | 0.0 | - |
|
| 336 |
+
| 27.6358 | 8650 | 0.0 | - |
|
| 337 |
+
| 27.7955 | 8700 | 0.0 | - |
|
| 338 |
+
| 27.9553 | 8750 | 0.0 | - |
|
| 339 |
+
| 28.1150 | 8800 | 0.0 | - |
|
| 340 |
+
| 28.2748 | 8850 | 0.0 | - |
|
| 341 |
+
| 28.4345 | 8900 | 0.0 | - |
|
| 342 |
+
| 28.5942 | 8950 | 0.0 | - |
|
| 343 |
+
| 28.7540 | 9000 | 0.0 | - |
|
| 344 |
+
| 28.9137 | 9050 | 0.0 | - |
|
| 345 |
+
| 29.0735 | 9100 | 0.0 | - |
|
| 346 |
+
| 29.2332 | 9150 | 0.0 | - |
|
| 347 |
+
| 29.3930 | 9200 | 0.0 | - |
|
| 348 |
+
| 29.5527 | 9250 | 0.0 | - |
|
| 349 |
+
| 29.7125 | 9300 | 0.0 | - |
|
| 350 |
+
| 29.8722 | 9350 | 0.0 | - |
|
| 351 |
+
|
| 352 |
+
### Framework Versions
|
| 353 |
+
- Python: 3.10.12
|
| 354 |
+
- SetFit: 1.1.0
|
| 355 |
+
- Sentence Transformers: 3.3.1
|
| 356 |
+
- Transformers: 4.44.2
|
| 357 |
+
- PyTorch: 2.2.0a0+81ea7a4
|
| 358 |
+
- Datasets: 3.2.0
|
| 359 |
+
- Tokenizers: 0.19.1
|
| 360 |
+
|
| 361 |
+
## Citation
|
| 362 |
+
|
| 363 |
+
### BibTeX
|
| 364 |
+
```bibtex
|
| 365 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
| 366 |
+
doi = {10.48550/ARXIV.2209.11055},
|
| 367 |
+
url = {https://arxiv.org/abs/2209.11055},
|
| 368 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
| 369 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
| 370 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
| 371 |
+
publisher = {arXiv},
|
| 372 |
+
year = {2022},
|
| 373 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
| 374 |
+
}
|
| 375 |
+
```
|
| 376 |
+
|
| 377 |
+
<!--
|
| 378 |
+
## Glossary
|
| 379 |
+
|
| 380 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 381 |
+
-->
|
| 382 |
+
|
| 383 |
+
<!--
|
| 384 |
+
## Model Card Authors
|
| 385 |
+
|
| 386 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 387 |
+
-->
|
| 388 |
+
|
| 389 |
+
<!--
|
| 390 |
+
## Model Card Contact
|
| 391 |
+
|
| 392 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 393 |
+
-->
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mini1013/master_item_bt_test_flat_top",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"tokenizer_class": "BertTokenizer",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.44.2",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.3.1",
|
| 4 |
+
"transformers": "4.44.2",
|
| 5 |
+
"pytorch": "2.2.0a0+81ea7a4"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": "cosine"
|
| 10 |
+
}
|
config_setfit.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"labels": null,
|
| 3 |
+
"normalize_embeddings": false
|
| 4 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4414160907aa69dfd11257716394b1a934a3e69128e354a9fc61580fc5ccfbc2
|
| 3 |
+
size 442494816
|
model_head.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d08dc087f984ec8b6fa177e99c460fa51cb1a3bb6f28db81aa8a2ef7b04d9b60
|
| 3 |
+
size 25479
|
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 |
+
]
|
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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[CLS]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 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 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_basic_tokenize": true,
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "[SEP]",
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"max_length": 512,
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"never_split": null,
|
| 54 |
+
"pad_to_multiple_of": null,
|
| 55 |
+
"pad_token": "[PAD]",
|
| 56 |
+
"pad_token_type_id": 0,
|
| 57 |
+
"padding_side": "right",
|
| 58 |
+
"sep_token": "[SEP]",
|
| 59 |
+
"stride": 0,
|
| 60 |
+
"strip_accents": null,
|
| 61 |
+
"tokenize_chinese_chars": true,
|
| 62 |
+
"tokenizer_class": "BertTokenizer",
|
| 63 |
+
"truncation_side": "right",
|
| 64 |
+
"truncation_strategy": "longest_first",
|
| 65 |
+
"unk_token": "[UNK]"
|
| 66 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|