Push model using huggingface_hub.
Browse files- 1_Pooling/config.json +10 -0
- README.md +736 -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 +1,736 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: klue/roberta-base
|
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: '[5월/롯데단독] 더 슬림 벨벳 래디컬 듀오 세트(+향수 미니어처) 1966호_1966호 LotteOn > 백화점 > 뷰티 > 상단
|
14 |
+
배너 (Mobile) LotteOn > 뷰티 > 메이크업 > 립메이크업 > 립스틱'
|
15 |
+
- text: 파이버윅 마스카라 + 볼륨 마스카라(브라운) 홈>MAKE-UP;(#M)홈>MAKE-UP>아이>마스카라 Naverstore > 화장품/미용
|
16 |
+
> 색조메이크업 > 마스카라
|
17 |
+
- text: MAC 러스터글래스 립스틱 오 구디 (#M)화장품/향수>색조메이크업>립스틱 Gmarket > 뷰티 > 화장품/향수 > 색조메이크업 >
|
18 |
+
립스틱
|
19 |
+
- text: 에르메스 루즈 새틴 립스틱 3.5g 64 LotteOn > 뷰티 > 색조메이크업 > 립메이크업 > 립스틱 LotteOn > 뷰티 >
|
20 |
+
색조메이크업 > 립메이크업 > 립스틱
|
21 |
+
- text: 프리사이슬리 마이 브로우 펜슬 세트(+브로우 디럭스 증정) 3.5 미디움 LotteOn > 뷰티 > 색조메이크업 > 아이메이크업 LotteOn
|
22 |
+
> 뷰티 > 메이크업 > 아이메이크업
|
23 |
+
inference: true
|
24 |
+
model-index:
|
25 |
+
- name: SetFit with klue/roberta-base
|
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: 0.8601678463697996
|
37 |
+
name: Accuracy
|
38 |
+
---
|
39 |
+
|
40 |
+
# SetFit with klue/roberta-base
|
41 |
+
|
42 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [klue/roberta-base](https://huggingface.co/klue/roberta-base) 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:** [klue/roberta-base](https://huggingface.co/klue/roberta-base)
|
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:** 11 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 |
+
| 0 | <ul><li>'[4월/SSG단독] 따뚜아쥬 꾸뛰르 벨벳 틴트 듀오 세트(+레드 키링 핸드미러) 211호_201호 LOREAL > DepartmentSsg > 입생로랑 > Branded > 따뚜아쥬 꾸뛰르 LOREAL > DepartmentSsg > 입생로랑 > Branded > 따뚜아쥬 꾸뛰르'</li><li>'롬앤 11번가 런칭! 모든 취향 취급 중! 밀크 그로서리 외 BEST 1+1 UP TO 65% 옵션33. 제로 벨벳 틴트_14 피칸 타르트 쇼킹딜 홈>뷰티>선케어/메이크업>립/치크메이크업;11st>메이크업>립메이크업>립틴트;11st>뷰티>선케어/메이크업>립/치크메이크업;11st>뷰티>선케어/메이크업>아이메이크업;11st>메이크업>���이메이크업>마스카라;11st Hour Event > 패션/뷰티 > 뷰티 > 선케어/메이크업 > 립/치크메이크업 11st Hour Event > 패션/뷰티 > 뷰티 > 선케어/메이크업 > 아이메이크업'</li><li>'[15% 즉시할인 + 1만원이상 10%할인] 메이블린 뉴욕 슈퍼스테이 립 잉크 2개 [증정]고급 엠보싱 화장솜 2개 175호 링리더_시커 ssg > 뷰티 > 헤어/바디 > 헤어케어 > 샴푸 ssg > 뷰티 > 헤어/바디 > 헤어케어 > 샴푸'</li></ul> |
|
71 |
+
| 4 | <ul><li>'비디보브 VDIVOV 아이컷 마스카라 02 롱앤볼륨 × 1개 Coupang > 뷰티 > 메이크업 > 아이 메이크업 > 마스카라;(#M)쿠팡 홈>뷰티>메이크업>아이 메이크업>마스카라 Coupang > 뷰티 > 메이크업 > 아이 메이크업 > 마스카라'</li><li>'이니스프리 스키니 꼼꼼 마스카라 Zero 3.5g 2호 브라운 × 1개 LotteOn > 뷰티 > 메이크업 > 아이메이크업 > 마스카라 LotteOn > 뷰티 > 메이크업 > 아이메이크업 > 마스카라'</li><li>'이니스프리 스키니 꼼꼼카라 2호 브라운 2개 MinSellAmount (#M)화장품/향수>색조메이크업>마스카라 Gmarket > 뷰티 > 화장품/향수 > 색조메이크업 > 마스카라'</li></ul> |
|
72 |
+
| 8 | <ul><li>'[단독] 브로우 파이버 젤 + 브로우 스타일러 세트 (+테크나콜 라이너 정품 & 픽서 샘플 ) 스트러트_플링 (#M)DepartmentSsg > MAC > EYE > BROW LOREAL > DepartmentSsg > 슈에무라 > Generic > 립스틱'</li><li>'Maybelline New York Brow Precise Shaping Eyebrow Pencil, Auburn, 0.02 oz. Deep Brown_One Size LotteOn > 뷰티 > 뷰티소품 > 아이소품 > 샤프너 LotteOn > 뷰티 > 뷰티소품 > 아이소품 > 샤프너'</li><li>'[K쇼핑][메이블린뉴욕] 디파인&블렌드 아이브로우 펜슬 0.16g 그레이브라운 LotteOn > 뷰티 > 뷰티기기 > 눈썹관리 > 눈썹정리기 LotteOn > 뷰티 > 뷰티기기 > 눈썹관리 > 눈썹정리기'</li></ul> |
|
73 |
+
| 9 | <ul><li>'컨실러 브러쉬 미디엄 176 단품없음 LotteOn > 뷰티 > 뷰티기기 > 액세서리/소모품 LotteOn > 뷰티 > 뷰티기기 > 액세서리/소모품'</li><li>'[에뛰드] 룩 앳 마이 아이즈 쿠키칩스 2g 카페BR437오븐넣고5분 홈>신제품🌹;홈>신제품;홈>아이>섀도우;(#M)홈>아이>전체 Naverstore > 화장품/미용 > 색조메이크업 > 아이섀도'</li><li>'아티스트 컬러 아이 섀도우 I-520 핑키 샌드 홈>★정품 증정 & 할인세트★;홈>★단 7일간! 특별세트★;홈>★SPECIAL SET★;홈>EYE;홈>아이 & 립;홈>■할인 & 단독세트■;홈>★단 하루 포인트혜택★;홈>15% OFF;홈>■단독 구성■;홈>■2021 역대급 구성■;홈>■네이버 단독구성■;(#M)홈>EYE & LIP Naverstore > 화장품/미용 > 색조메이크업 > 아이섀도'</li></ul> |
|
74 |
+
| 6 | <ul><li>'쓰리씨이 (3CE X TOILETPAPER) 3CE 페이스 블러쉬 LET ME STAY_FRE (#M)화장품/향수>색조메이크업>블러셔 Gmarket > 뷰티 > 화장품/향수 > 색조메이크업 > 블러셔'</li><li>'[베네피트] [태연픽] 베네피트 WANDERful World 블러쉬 & BOP 미니 9종 택1 피친 미니 (#M)11st>메이크업>치크/하이라이터>치크/블러셔 11st > 뷰티 > 메이크업 > 치크/하이라이터'</li><li>'로라메르시에 블러쉬 컬러 인퓨전 구아바 LotteOn > 뷰티 > 메이크업 > 블러셔 LotteOn > 뷰티 > 메이크업 > 블러셔'</li></ul> |
|
75 |
+
| 1 | <ul><li>'[LG뷰티]비디보브 립컷 라이너 PK102 그런지 핑크 (#M)홈>화장품/미용>메이크업>립메이크업>립라이너 HMALL > 뷰티 > 화장품/미용 > 메이크업 > 립메이크업 > 립라이너'</li><li>'조르지오 아르마니 스무스 실크 립 펜슬 - 06 1.14g (#M)11st>선케어>선밤>선밤 11st > 뷰티 > 선케어 > 선밤 > 선밤'</li><li>'Maybelline New York Maybelline New York Color Sensational Shaping Lip Liner Makeup, Pink Wink, 0.01 LotteOn > 뷰티 > 색조메이크업 > 색조메이크업세트 LotteOn > 뷰티 > 색조메이크업 > 색조메이크업세트'</li></ul> |
|
76 |
+
| 3 | <ul><li>'[온세일]페탈 키스 립스틱 4g (옵션) 01 딥로즈 LotteOn > 뷰티 > 색조메이크업 > 립메이크업 LotteOn > 뷰티 > 메이크업 > 립메이크업 > 립틴트'</li><li>'에스쁘아 컬러풀 누드 립스틱 노웨어 3.5g 4호 메멘토 × 1개 쿠팡 홈>선물스토어>생일선물>여성선물>화장품>립스틱;쿠팡 홈>선물스토어>생일>화장품>립스틱;Coupang > 뷰티 > 메이크업 > 립 메이크업;(#M)쿠팡 홈>뷰티>메이크업>립 메이크업>립스틱 Coupang > 뷰티 > 로드샵 > 메이크업 > 립 메이크업 > 립스틱'</li><li>'[4월/SSG단독] 루쥬 볼립떼 샤인 듀오 세트(+레드 키링 핸드미러) 83호_154호 LOREAL > DepartmentSsg > 입생로랑 > Branded > 입생로랑 LOREAL > DepartmentSsg > 입생로랑 > Branded > 입생로랑'</li></ul> |
|
77 |
+
| 7 | <ul><li>'퍼펙트 디자이닝 아이라이너 펜슬 아이라이너 워터프루프 펜슬_03_딥 블랙 (#M)뷰티>화장품/향수>포인트메이크업>아이라이너 CJmall > 뷰티 > 화장품/향수 > 포인트메이크업 > 아이라이너'</li><li>'미샤 팔레트 페인트 라이너 6ml 02 브라운 홈>전체상품;홈>네이처리퍼블릭;(#M)홈>미샤 Naverstore > 화장품/미용 > 색조메이크업 > 아이라이너 > 젤형'</li><li>'리르 리얼 타투펜 아이라이너 리얼펜_딥블랙 ssg > 뷰티 > 메이크업 > 아이메이크업 > 아이라이너 ssg > 뷰티 > 메이크업 > 아이메이크업 > 아이라이너'</li></ul> |
|
78 |
+
| 10 | <ul><li>'Maybelline New York Facestudio Master Chrome Metallic Highlighter Makeup Molten Topaz 019 Ounce Molten Topaz_One Size (#M)SSG.COM/미용기기/소품/메이크업브러쉬/페이스브러쉬 ssg > 뷰티 > 미용기기/소품 > 메이크업브러쉬 > 페이스브러쉬'</li><li>'페리페라 잉크 브이 쉐딩 [단품]003 헤이즐그레이 홈>메이크업>베이스>쉐이딩/컨투어링;(#M)홈>메이크업>베이스메이크업>쉐이딩/컨투어링 OLIVEYOUNG > 메이크업 > 베이스메이크업 > 쉐이딩/컨투어링'</li><li>'샤넬 바움 에쌍씨엘 멀티 스틱 8g 2종 1. 스컬프팅 Sculpting 홈>화장품/미용>색조메이크업>하이라이터;(#M)홈>화장품/미용>색조메이크업>하이라이터/쉐이딩 Naverstore > 화장품/미용 > 색조메이크업 > 하이라이터/쉐이딩'</li></ul> |
|
79 |
+
| 2 | <ul><li>'유리아쥬 제모스 무향 스틱 3개 무향 × 3개 (#M)쿠팡 홈>뷰티>메이크업>립 메이크업>립케어 Coupang > 뷰티 > 메이크업 > 립 메이크업 > 립케어'</li><li>'(+필로우케이스 )버츠비 틴티드립밤 x2 6종 택2 01_로즈_03_매그놀리아 (#M)GSSHOP>뷰티>포인트메이크업>립케어 GSSHOP > 뷰티 > 포인트메이크업 > 립케어'</li><li>'[각인서비스/벨벳파우치 증정] 봄 데 뮤제 립 밤 7g 레드_바이올렛 파우치_개인화 문구(특수문자 포함 최대 4글자/배송메세지 기재) ssg > 뷰티 > 향수 > 여성향수;ssg > 뷰티 > 스킨케어 > 립케어 ssg > 뷰티 > 메이크업 > 립메이크업'</li></ul> |
|
80 |
+
| 5 | <ul><li>'5 꿀뢰르 꾸뛰르 079 블랙 보우 LotteOn > 뷰티 > 명품화장품 > 메이크업 LotteOn > 뷰티 > 메이크업 > 아이메이크업 > 아이섀도우'</li><li>'[뽀샵브러쉬] 블러쉬 브러쉬 키트 160 단품없음 LotteOn > 뷰티 > 뷰티기기 > 액세서리/소모품 LotteOn > 뷰티 > 뷰티기기 > 액세서리/소모품'</li><li>'퓨어 컬러 엔비 립스틱 크림 - 블레임레스 ssg > 뷰티 > 메이크업 > 립메이크업 ssg > 뷰티 > 메이크업 > 립메이크업 > 립스틱'</li></ul> |
|
81 |
+
|
82 |
+
## Evaluation
|
83 |
+
|
84 |
+
### Metrics
|
85 |
+
| Label | Accuracy |
|
86 |
+
|:--------|:---------|
|
87 |
+
| **all** | 0.8602 |
|
88 |
+
|
89 |
+
## Uses
|
90 |
+
|
91 |
+
### Direct Use for Inference
|
92 |
+
|
93 |
+
First install the SetFit library:
|
94 |
+
|
95 |
+
```bash
|
96 |
+
pip install setfit
|
97 |
+
```
|
98 |
+
|
99 |
+
Then you can load this model and run inference.
|
100 |
+
|
101 |
+
```python
|
102 |
+
from setfit import SetFitModel
|
103 |
+
|
104 |
+
# Download from the 🤗 Hub
|
105 |
+
model = SetFitModel.from_pretrained("mini1013/master_item_top_bt7")
|
106 |
+
# Run inference
|
107 |
+
preds = model("MAC 러스터글래스 립스틱 오 구디 (#M)화장품/향수>색조메이크업>립스틱 Gmarket > 뷰티 > 화장품/향수 > 색조메이크업 > 립스틱")
|
108 |
+
```
|
109 |
+
|
110 |
+
<!--
|
111 |
+
### Downstream Use
|
112 |
+
|
113 |
+
*List how someone could finetune this model on their own dataset.*
|
114 |
+
-->
|
115 |
+
|
116 |
+
<!--
|
117 |
+
### Out-of-Scope Use
|
118 |
+
|
119 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
120 |
+
-->
|
121 |
+
|
122 |
+
<!--
|
123 |
+
## Bias, Risks and Limitations
|
124 |
+
|
125 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
126 |
+
-->
|
127 |
+
|
128 |
+
<!--
|
129 |
+
### Recommendations
|
130 |
+
|
131 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
132 |
+
-->
|
133 |
+
|
134 |
+
## Training Details
|
135 |
+
|
136 |
+
### Training Set Metrics
|
137 |
+
| Training set | Min | Median | Max |
|
138 |
+
|:-------------|:----|:--------|:----|
|
139 |
+
| Word count | 10 | 23.2382 | 81 |
|
140 |
+
|
141 |
+
| Label | Training Sample Count |
|
142 |
+
|:------|:----------------------|
|
143 |
+
| 0 | 50 |
|
144 |
+
| 1 | 50 |
|
145 |
+
| 2 | 50 |
|
146 |
+
| 3 | 50 |
|
147 |
+
| 4 | 50 |
|
148 |
+
| 5 | 50 |
|
149 |
+
| 6 | 50 |
|
150 |
+
| 7 | 50 |
|
151 |
+
| 8 | 50 |
|
152 |
+
| 9 | 50 |
|
153 |
+
| 10 | 50 |
|
154 |
+
|
155 |
+
### Training Hyperparameters
|
156 |
+
- batch_size: (64, 64)
|
157 |
+
- num_epochs: (30, 30)
|
158 |
+
- max_steps: -1
|
159 |
+
- sampling_strategy: oversampling
|
160 |
+
- num_iterations: 100
|
161 |
+
- body_learning_rate: (2e-05, 1e-05)
|
162 |
+
- head_learning_rate: 0.01
|
163 |
+
- loss: CosineSimilarityLoss
|
164 |
+
- distance_metric: cosine_distance
|
165 |
+
- margin: 0.25
|
166 |
+
- end_to_end: False
|
167 |
+
- use_amp: False
|
168 |
+
- warmup_proportion: 0.1
|
169 |
+
- l2_weight: 0.01
|
170 |
+
- seed: 42
|
171 |
+
- eval_max_steps: -1
|
172 |
+
- load_best_model_at_end: False
|
173 |
+
|
174 |
+
### Training Results
|
175 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
176 |
+
|:-------:|:-----:|:-------------:|:---------------:|
|
177 |
+
| 0.0012 | 1 | 0.4386 | - |
|
178 |
+
| 0.0581 | 50 | 0.4443 | - |
|
179 |
+
| 0.1163 | 100 | 0.4215 | - |
|
180 |
+
| 0.1744 | 150 | 0.3998 | - |
|
181 |
+
| 0.2326 | 200 | 0.3843 | - |
|
182 |
+
| 0.2907 | 250 | 0.3551 | - |
|
183 |
+
| 0.3488 | 300 | 0.3063 | - |
|
184 |
+
| 0.4070 | 350 | 0.2439 | - |
|
185 |
+
| 0.4651 | 400 | 0.1803 | - |
|
186 |
+
| 0.5233 | 450 | 0.1286 | - |
|
187 |
+
| 0.5814 | 500 | 0.0885 | - |
|
188 |
+
| 0.6395 | 550 | 0.0653 | - |
|
189 |
+
| 0.6977 | 600 | 0.0515 | - |
|
190 |
+
| 0.7558 | 650 | 0.034 | - |
|
191 |
+
| 0.8140 | 700 | 0.0305 | - |
|
192 |
+
| 0.8721 | 750 | 0.0291 | - |
|
193 |
+
| 0.9302 | 800 | 0.028 | - |
|
194 |
+
| 0.9884 | 850 | 0.028 | - |
|
195 |
+
| 1.0465 | 900 | 0.0249 | - |
|
196 |
+
| 1.1047 | 950 | 0.0242 | - |
|
197 |
+
| 1.1628 | 1000 | 0.0244 | - |
|
198 |
+
| 1.2209 | 1050 | 0.0173 | - |
|
199 |
+
| 1.2791 | 1100 | 0.0099 | - |
|
200 |
+
| 1.3372 | 1150 | 0.0063 | - |
|
201 |
+
| 1.3953 | 1200 | 0.0038 | - |
|
202 |
+
| 1.4535 | 1250 | 0.0009 | - |
|
203 |
+
| 1.5116 | 1300 | 0.0005 | - |
|
204 |
+
| 1.5698 | 1350 | 0.0004 | - |
|
205 |
+
| 1.6279 | 1400 | 0.0004 | - |
|
206 |
+
| 1.6860 | 1450 | 0.0003 | - |
|
207 |
+
| 1.7442 | 1500 | 0.0003 | - |
|
208 |
+
| 1.8023 | 1550 | 0.0004 | - |
|
209 |
+
| 1.8605 | 1600 | 0.0005 | - |
|
210 |
+
| 1.9186 | 1650 | 0.0003 | - |
|
211 |
+
| 1.9767 | 1700 | 0.0002 | - |
|
212 |
+
| 2.0349 | 1750 | 0.0001 | - |
|
213 |
+
| 2.0930 | 1800 | 0.0001 | - |
|
214 |
+
| 2.1512 | 1850 | 0.0001 | - |
|
215 |
+
| 2.2093 | 1900 | 0.0001 | - |
|
216 |
+
| 2.2674 | 1950 | 0.0001 | - |
|
217 |
+
| 2.3256 | 2000 | 0.0001 | - |
|
218 |
+
| 2.3837 | 2050 | 0.0001 | - |
|
219 |
+
| 2.4419 | 2100 | 0.0001 | - |
|
220 |
+
| 2.5 | 2150 | 0.0001 | - |
|
221 |
+
| 2.5581 | 2200 | 0.0001 | - |
|
222 |
+
| 2.6163 | 2250 | 0.0001 | - |
|
223 |
+
| 2.6744 | 2300 | 0.0001 | - |
|
224 |
+
| 2.7326 | 2350 | 0.0007 | - |
|
225 |
+
| 2.7907 | 2400 | 0.0028 | - |
|
226 |
+
| 2.8488 | 2450 | 0.0016 | - |
|
227 |
+
| 2.9070 | 2500 | 0.0015 | - |
|
228 |
+
| 2.9651 | 2550 | 0.0026 | - |
|
229 |
+
| 3.0233 | 2600 | 0.0001 | - |
|
230 |
+
| 3.0814 | 2650 | 0.0001 | - |
|
231 |
+
| 3.1395 | 2700 | 0.0001 | - |
|
232 |
+
| 3.1977 | 2750 | 0.0 | - |
|
233 |
+
| 3.2558 | 2800 | 0.0002 | - |
|
234 |
+
| 3.3140 | 2850 | 0.0003 | - |
|
235 |
+
| 3.3721 | 2900 | 0.0 | - |
|
236 |
+
| 3.4302 | 2950 | 0.0 | - |
|
237 |
+
| 3.4884 | 3000 | 0.0 | - |
|
238 |
+
| 3.5465 | 3050 | 0.0 | - |
|
239 |
+
| 3.6047 | 3100 | 0.0 | - |
|
240 |
+
| 3.6628 | 3150 | 0.0 | - |
|
241 |
+
| 3.7209 | 3200 | 0.0 | - |
|
242 |
+
| 3.7791 | 3250 | 0.0 | - |
|
243 |
+
| 3.8372 | 3300 | 0.0 | - |
|
244 |
+
| 3.8953 | 3350 | 0.0 | - |
|
245 |
+
| 3.9535 | 3400 | 0.0 | - |
|
246 |
+
| 4.0116 | 3450 | 0.0 | - |
|
247 |
+
| 4.0698 | 3500 | 0.0 | - |
|
248 |
+
| 4.1279 | 3550 | 0.0 | - |
|
249 |
+
| 4.1860 | 3600 | 0.0 | - |
|
250 |
+
| 4.2442 | 3650 | 0.0 | - |
|
251 |
+
| 4.3023 | 3700 | 0.0 | - |
|
252 |
+
| 4.3605 | 3750 | 0.0 | - |
|
253 |
+
| 4.4186 | 3800 | 0.0 | - |
|
254 |
+
| 4.4767 | 3850 | 0.0 | - |
|
255 |
+
| 4.5349 | 3900 | 0.0 | - |
|
256 |
+
| 4.5930 | 3950 | 0.0 | - |
|
257 |
+
| 4.6512 | 4000 | 0.0 | - |
|
258 |
+
| 4.7093 | 4050 | 0.0 | - |
|
259 |
+
| 4.7674 | 4100 | 0.0 | - |
|
260 |
+
| 4.8256 | 4150 | 0.0 | - |
|
261 |
+
| 4.8837 | 4200 | 0.0 | - |
|
262 |
+
| 4.9419 | 4250 | 0.0 | - |
|
263 |
+
| 5.0 | 4300 | 0.0 | - |
|
264 |
+
| 5.0581 | 4350 | 0.0 | - |
|
265 |
+
| 5.1163 | 4400 | 0.0 | - |
|
266 |
+
| 5.1744 | 4450 | 0.0 | - |
|
267 |
+
| 5.2326 | 4500 | 0.0 | - |
|
268 |
+
| 5.2907 | 4550 | 0.0 | - |
|
269 |
+
| 5.3488 | 4600 | 0.0 | - |
|
270 |
+
| 5.4070 | 4650 | 0.0 | - |
|
271 |
+
| 5.4651 | 4700 | 0.0 | - |
|
272 |
+
| 5.5233 | 4750 | 0.0 | - |
|
273 |
+
| 5.5814 | 4800 | 0.0 | - |
|
274 |
+
| 5.6395 | 4850 | 0.0 | - |
|
275 |
+
| 5.6977 | 4900 | 0.0 | - |
|
276 |
+
| 5.7558 | 4950 | 0.0 | - |
|
277 |
+
| 5.8140 | 5000 | 0.0 | - |
|
278 |
+
| 5.8721 | 5050 | 0.0 | - |
|
279 |
+
| 5.9302 | 5100 | 0.0 | - |
|
280 |
+
| 5.9884 | 5150 | 0.0 | - |
|
281 |
+
| 6.0465 | 5200 | 0.0 | - |
|
282 |
+
| 6.1047 | 5250 | 0.0 | - |
|
283 |
+
| 6.1628 | 5300 | 0.0 | - |
|
284 |
+
| 6.2209 | 5350 | 0.0 | - |
|
285 |
+
| 6.2791 | 5400 | 0.0 | - |
|
286 |
+
| 6.3372 | 5450 | 0.0 | - |
|
287 |
+
| 6.3953 | 5500 | 0.0 | - |
|
288 |
+
| 6.4535 | 5550 | 0.0 | - |
|
289 |
+
| 6.5116 | 5600 | 0.0 | - |
|
290 |
+
| 6.5698 | 5650 | 0.0 | - |
|
291 |
+
| 6.6279 | 5700 | 0.0 | - |
|
292 |
+
| 6.6860 | 5750 | 0.0 | - |
|
293 |
+
| 6.7442 | 5800 | 0.0 | - |
|
294 |
+
| 6.8023 | 5850 | 0.0 | - |
|
295 |
+
| 6.8605 | 5900 | 0.0 | - |
|
296 |
+
| 6.9186 | 5950 | 0.0 | - |
|
297 |
+
| 6.9767 | 6000 | 0.0 | - |
|
298 |
+
| 7.0349 | 6050 | 0.0 | - |
|
299 |
+
| 7.0930 | 6100 | 0.0 | - |
|
300 |
+
| 7.1512 | 6150 | 0.0 | - |
|
301 |
+
| 7.2093 | 6200 | 0.0 | - |
|
302 |
+
| 7.2674 | 6250 | 0.0 | - |
|
303 |
+
| 7.3256 | 6300 | 0.0 | - |
|
304 |
+
| 7.3837 | 6350 | 0.0 | - |
|
305 |
+
| 7.4419 | 6400 | 0.0 | - |
|
306 |
+
| 7.5 | 6450 | 0.0 | - |
|
307 |
+
| 7.5581 | 6500 | 0.0 | - |
|
308 |
+
| 7.6163 | 6550 | 0.0 | - |
|
309 |
+
| 7.6744 | 6600 | 0.0 | - |
|
310 |
+
| 7.7326 | 6650 | 0.0 | - |
|
311 |
+
| 7.7907 | 6700 | 0.0 | - |
|
312 |
+
| 7.8488 | 6750 | 0.0 | - |
|
313 |
+
| 7.9070 | 6800 | 0.0 | - |
|
314 |
+
| 7.9651 | 6850 | 0.0 | - |
|
315 |
+
| 8.0233 | 6900 | 0.0 | - |
|
316 |
+
| 8.0814 | 6950 | 0.0 | - |
|
317 |
+
| 8.1395 | 7000 | 0.0 | - |
|
318 |
+
| 8.1977 | 7050 | 0.0 | - |
|
319 |
+
| 8.2558 | 7100 | 0.0 | - |
|
320 |
+
| 8.3140 | 7150 | 0.0 | - |
|
321 |
+
| 8.3721 | 7200 | 0.0 | - |
|
322 |
+
| 8.4302 | 7250 | 0.0 | - |
|
323 |
+
| 8.4884 | 7300 | 0.0 | - |
|
324 |
+
| 8.5465 | 7350 | 0.0 | - |
|
325 |
+
| 8.6047 | 7400 | 0.0 | - |
|
326 |
+
| 8.6628 | 7450 | 0.0 | - |
|
327 |
+
| 8.7209 | 7500 | 0.0 | - |
|
328 |
+
| 8.7791 | 7550 | 0.0 | - |
|
329 |
+
| 8.8372 | 7600 | 0.0 | - |
|
330 |
+
| 8.8953 | 7650 | 0.0 | - |
|
331 |
+
| 8.9535 | 7700 | 0.0 | - |
|
332 |
+
| 9.0116 | 7750 | 0.0 | - |
|
333 |
+
| 9.0698 | 7800 | 0.0 | - |
|
334 |
+
| 9.1279 | 7850 | 0.0 | - |
|
335 |
+
| 9.1860 | 7900 | 0.0 | - |
|
336 |
+
| 9.2442 | 7950 | 0.0 | - |
|
337 |
+
| 9.3023 | 8000 | 0.0 | - |
|
338 |
+
| 9.3605 | 8050 | 0.0 | - |
|
339 |
+
| 9.4186 | 8100 | 0.0 | - |
|
340 |
+
| 9.4767 | 8150 | 0.0 | - |
|
341 |
+
| 9.5349 | 8200 | 0.0 | - |
|
342 |
+
| 9.5930 | 8250 | 0.0 | - |
|
343 |
+
| 9.6512 | 8300 | 0.0 | - |
|
344 |
+
| 9.7093 | 8350 | 0.0 | - |
|
345 |
+
| 9.7674 | 8400 | 0.0 | - |
|
346 |
+
| 9.8256 | 8450 | 0.0 | - |
|
347 |
+
| 9.8837 | 8500 | 0.0 | - |
|
348 |
+
| 9.9419 | 8550 | 0.0 | - |
|
349 |
+
| 10.0 | 8600 | 0.0 | - |
|
350 |
+
| 10.0581 | 8650 | 0.0 | - |
|
351 |
+
| 10.1163 | 8700 | 0.0 | - |
|
352 |
+
| 10.1744 | 8750 | 0.0 | - |
|
353 |
+
| 10.2326 | 8800 | 0.0 | - |
|
354 |
+
| 10.2907 | 8850 | 0.0 | - |
|
355 |
+
| 10.3488 | 8900 | 0.0 | - |
|
356 |
+
| 10.4070 | 8950 | 0.0 | - |
|
357 |
+
| 10.4651 | 9000 | 0.0 | - |
|
358 |
+
| 10.5233 | 9050 | 0.0 | - |
|
359 |
+
| 10.5814 | 9100 | 0.0 | - |
|
360 |
+
| 10.6395 | 9150 | 0.0 | - |
|
361 |
+
| 10.6977 | 9200 | 0.0241 | - |
|
362 |
+
| 10.7558 | 9250 | 0.0134 | - |
|
363 |
+
| 10.8140 | 9300 | 0.0109 | - |
|
364 |
+
| 10.8721 | 9350 | 0.0096 | - |
|
365 |
+
| 10.9302 | 9400 | 0.009 | - |
|
366 |
+
| 10.9884 | 9450 | 0.0083 | - |
|
367 |
+
| 11.0465 | 9500 | 0.0115 | - |
|
368 |
+
| 11.1047 | 9550 | 0.0086 | - |
|
369 |
+
| 11.1628 | 9600 | 0.0043 | - |
|
370 |
+
| 11.2209 | 9650 | 0.0002 | - |
|
371 |
+
| 11.2791 | 9700 | 0.0005 | - |
|
372 |
+
| 11.3372 | 9750 | 0.0001 | - |
|
373 |
+
| 11.3953 | 9800 | 0.0 | - |
|
374 |
+
| 11.4535 | 9850 | 0.0 | - |
|
375 |
+
| 11.5116 | 9900 | 0.0 | - |
|
376 |
+
| 11.5698 | 9950 | 0.0 | - |
|
377 |
+
| 11.6279 | 10000 | 0.0 | - |
|
378 |
+
| 11.6860 | 10050 | 0.0 | - |
|
379 |
+
| 11.7442 | 10100 | 0.0 | - |
|
380 |
+
| 11.8023 | 10150 | 0.0 | - |
|
381 |
+
| 11.8605 | 10200 | 0.0 | - |
|
382 |
+
| 11.9186 | 10250 | 0.0 | - |
|
383 |
+
| 11.9767 | 10300 | 0.0 | - |
|
384 |
+
| 12.0349 | 10350 | 0.0 | - |
|
385 |
+
| 12.0930 | 10400 | 0.0 | - |
|
386 |
+
| 12.1512 | 10450 | 0.0 | - |
|
387 |
+
| 12.2093 | 10500 | 0.0 | - |
|
388 |
+
| 12.2674 | 10550 | 0.0 | - |
|
389 |
+
| 12.3256 | 10600 | 0.0 | - |
|
390 |
+
| 12.3837 | 10650 | 0.0 | - |
|
391 |
+
| 12.4419 | 10700 | 0.0 | - |
|
392 |
+
| 12.5 | 10750 | 0.0 | - |
|
393 |
+
| 12.5581 | 10800 | 0.0 | - |
|
394 |
+
| 12.6163 | 10850 | 0.0 | - |
|
395 |
+
| 12.6744 | 10900 | 0.0 | - |
|
396 |
+
| 12.7326 | 10950 | 0.0 | - |
|
397 |
+
| 12.7907 | 11000 | 0.0 | - |
|
398 |
+
| 12.8488 | 11050 | 0.0 | - |
|
399 |
+
| 12.9070 | 11100 | 0.0 | - |
|
400 |
+
| 12.9651 | 11150 | 0.0 | - |
|
401 |
+
| 13.0233 | 11200 | 0.0 | - |
|
402 |
+
| 13.0814 | 11250 | 0.0 | - |
|
403 |
+
| 13.1395 | 11300 | 0.0 | - |
|
404 |
+
| 13.1977 | 11350 | 0.0 | - |
|
405 |
+
| 13.2558 | 11400 | 0.0 | - |
|
406 |
+
| 13.3140 | 11450 | 0.0 | - |
|
407 |
+
| 13.3721 | 11500 | 0.0 | - |
|
408 |
+
| 13.4302 | 11550 | 0.0 | - |
|
409 |
+
| 13.4884 | 11600 | 0.0 | - |
|
410 |
+
| 13.5465 | 11650 | 0.0 | - |
|
411 |
+
| 13.6047 | 11700 | 0.0 | - |
|
412 |
+
| 13.6628 | 11750 | 0.0 | - |
|
413 |
+
| 13.7209 | 11800 | 0.0 | - |
|
414 |
+
| 13.7791 | 11850 | 0.0 | - |
|
415 |
+
| 13.8372 | 11900 | 0.0 | - |
|
416 |
+
| 13.8953 | 11950 | 0.0 | - |
|
417 |
+
| 13.9535 | 12000 | 0.0 | - |
|
418 |
+
| 14.0116 | 12050 | 0.0 | - |
|
419 |
+
| 14.0698 | 12100 | 0.0 | - |
|
420 |
+
| 14.1279 | 12150 | 0.0 | - |
|
421 |
+
| 14.1860 | 12200 | 0.0 | - |
|
422 |
+
| 14.2442 | 12250 | 0.0 | - |
|
423 |
+
| 14.3023 | 12300 | 0.0 | - |
|
424 |
+
| 14.3605 | 12350 | 0.0 | - |
|
425 |
+
| 14.4186 | 12400 | 0.0 | - |
|
426 |
+
| 14.4767 | 12450 | 0.0 | - |
|
427 |
+
| 14.5349 | 12500 | 0.0 | - |
|
428 |
+
| 14.5930 | 12550 | 0.0 | - |
|
429 |
+
| 14.6512 | 12600 | 0.0 | - |
|
430 |
+
| 14.7093 | 12650 | 0.0 | - |
|
431 |
+
| 14.7674 | 12700 | 0.0 | - |
|
432 |
+
| 14.8256 | 12750 | 0.0 | - |
|
433 |
+
| 14.8837 | 12800 | 0.0 | - |
|
434 |
+
| 14.9419 | 12850 | 0.0 | - |
|
435 |
+
| 15.0 | 12900 | 0.0 | - |
|
436 |
+
| 15.0581 | 12950 | 0.0 | - |
|
437 |
+
| 15.1163 | 13000 | 0.0 | - |
|
438 |
+
| 15.1744 | 13050 | 0.0 | - |
|
439 |
+
| 15.2326 | 13100 | 0.0 | - |
|
440 |
+
| 15.2907 | 13150 | 0.0 | - |
|
441 |
+
| 15.3488 | 13200 | 0.0 | - |
|
442 |
+
| 15.4070 | 13250 | 0.0 | - |
|
443 |
+
| 15.4651 | 13300 | 0.0 | - |
|
444 |
+
| 15.5233 | 13350 | 0.0 | - |
|
445 |
+
| 15.5814 | 13400 | 0.0 | - |
|
446 |
+
| 15.6395 | 13450 | 0.0 | - |
|
447 |
+
| 15.6977 | 13500 | 0.0 | - |
|
448 |
+
| 15.7558 | 13550 | 0.0 | - |
|
449 |
+
| 15.8140 | 13600 | 0.0 | - |
|
450 |
+
| 15.8721 | 13650 | 0.0 | - |
|
451 |
+
| 15.9302 | 13700 | 0.0 | - |
|
452 |
+
| 15.9884 | 13750 | 0.0 | - |
|
453 |
+
| 16.0465 | 13800 | 0.0 | - |
|
454 |
+
| 16.1047 | 13850 | 0.0 | - |
|
455 |
+
| 16.1628 | 13900 | 0.0 | - |
|
456 |
+
| 16.2209 | 13950 | 0.0 | - |
|
457 |
+
| 16.2791 | 14000 | 0.0 | - |
|
458 |
+
| 16.3372 | 14050 | 0.0 | - |
|
459 |
+
| 16.3953 | 14100 | 0.0 | - |
|
460 |
+
| 16.4535 | 14150 | 0.0 | - |
|
461 |
+
| 16.5116 | 14200 | 0.0 | - |
|
462 |
+
| 16.5698 | 14250 | 0.0 | - |
|
463 |
+
| 16.6279 | 14300 | 0.0 | - |
|
464 |
+
| 16.6860 | 14350 | 0.0 | - |
|
465 |
+
| 16.7442 | 14400 | 0.0 | - |
|
466 |
+
| 16.8023 | 14450 | 0.0 | - |
|
467 |
+
| 16.8605 | 14500 | 0.0 | - |
|
468 |
+
| 16.9186 | 14550 | 0.0 | - |
|
469 |
+
| 16.9767 | 14600 | 0.0 | - |
|
470 |
+
| 17.0349 | 14650 | 0.0 | - |
|
471 |
+
| 17.0930 | 14700 | 0.0 | - |
|
472 |
+
| 17.1512 | 14750 | 0.0 | - |
|
473 |
+
| 17.2093 | 14800 | 0.0 | - |
|
474 |
+
| 17.2674 | 14850 | 0.0 | - |
|
475 |
+
| 17.3256 | 14900 | 0.0 | - |
|
476 |
+
| 17.3837 | 14950 | 0.0 | - |
|
477 |
+
| 17.4419 | 15000 | 0.0 | - |
|
478 |
+
| 17.5 | 15050 | 0.0 | - |
|
479 |
+
| 17.5581 | 15100 | 0.0 | - |
|
480 |
+
| 17.6163 | 15150 | 0.0 | - |
|
481 |
+
| 17.6744 | 15200 | 0.0 | - |
|
482 |
+
| 17.7326 | 15250 | 0.0 | - |
|
483 |
+
| 17.7907 | 15300 | 0.0 | - |
|
484 |
+
| 17.8488 | 15350 | 0.0 | - |
|
485 |
+
| 17.9070 | 15400 | 0.0 | - |
|
486 |
+
| 17.9651 | 15450 | 0.0 | - |
|
487 |
+
| 18.0233 | 15500 | 0.0 | - |
|
488 |
+
| 18.0814 | 15550 | 0.0 | - |
|
489 |
+
| 18.1395 | 15600 | 0.0 | - |
|
490 |
+
| 18.1977 | 15650 | 0.0 | - |
|
491 |
+
| 18.2558 | 15700 | 0.0 | - |
|
492 |
+
| 18.3140 | 15750 | 0.0 | - |
|
493 |
+
| 18.3721 | 15800 | 0.0 | - |
|
494 |
+
| 18.4302 | 15850 | 0.0 | - |
|
495 |
+
| 18.4884 | 15900 | 0.0 | - |
|
496 |
+
| 18.5465 | 15950 | 0.0 | - |
|
497 |
+
| 18.6047 | 16000 | 0.0 | - |
|
498 |
+
| 18.6628 | 16050 | 0.0 | - |
|
499 |
+
| 18.7209 | 16100 | 0.0 | - |
|
500 |
+
| 18.7791 | 16150 | 0.0 | - |
|
501 |
+
| 18.8372 | 16200 | 0.0 | - |
|
502 |
+
| 18.8953 | 16250 | 0.0 | - |
|
503 |
+
| 18.9535 | 16300 | 0.0 | - |
|
504 |
+
| 19.0116 | 16350 | 0.0 | - |
|
505 |
+
| 19.0698 | 16400 | 0.0 | - |
|
506 |
+
| 19.1279 | 16450 | 0.0 | - |
|
507 |
+
| 19.1860 | 16500 | 0.0 | - |
|
508 |
+
| 19.2442 | 16550 | 0.0 | - |
|
509 |
+
| 19.3023 | 16600 | 0.0 | - |
|
510 |
+
| 19.3605 | 16650 | 0.0 | - |
|
511 |
+
| 19.4186 | 16700 | 0.0 | - |
|
512 |
+
| 19.4767 | 16750 | 0.0 | - |
|
513 |
+
| 19.5349 | 16800 | 0.0 | - |
|
514 |
+
| 19.5930 | 16850 | 0.0 | - |
|
515 |
+
| 19.6512 | 16900 | 0.0 | - |
|
516 |
+
| 19.7093 | 16950 | 0.0 | - |
|
517 |
+
| 19.7674 | 17000 | 0.0 | - |
|
518 |
+
| 19.8256 | 17050 | 0.0 | - |
|
519 |
+
| 19.8837 | 17100 | 0.0 | - |
|
520 |
+
| 19.9419 | 17150 | 0.0 | - |
|
521 |
+
| 20.0 | 17200 | 0.0 | - |
|
522 |
+
| 20.0581 | 17250 | 0.0 | - |
|
523 |
+
| 20.1163 | 17300 | 0.0 | - |
|
524 |
+
| 20.1744 | 17350 | 0.0 | - |
|
525 |
+
| 20.2326 | 17400 | 0.0 | - |
|
526 |
+
| 20.2907 | 17450 | 0.0 | - |
|
527 |
+
| 20.3488 | 17500 | 0.0 | - |
|
528 |
+
| 20.4070 | 17550 | 0.0 | - |
|
529 |
+
| 20.4651 | 17600 | 0.0 | - |
|
530 |
+
| 20.5233 | 17650 | 0.0 | - |
|
531 |
+
| 20.5814 | 17700 | 0.0 | - |
|
532 |
+
| 20.6395 | 17750 | 0.0 | - |
|
533 |
+
| 20.6977 | 17800 | 0.0 | - |
|
534 |
+
| 20.7558 | 17850 | 0.0 | - |
|
535 |
+
| 20.8140 | 17900 | 0.0 | - |
|
536 |
+
| 20.8721 | 17950 | 0.0 | - |
|
537 |
+
| 20.9302 | 18000 | 0.0 | - |
|
538 |
+
| 20.9884 | 18050 | 0.0 | - |
|
539 |
+
| 21.0465 | 18100 | 0.0 | - |
|
540 |
+
| 21.1047 | 18150 | 0.0 | - |
|
541 |
+
| 21.1628 | 18200 | 0.0 | - |
|
542 |
+
| 21.2209 | 18250 | 0.0 | - |
|
543 |
+
| 21.2791 | 18300 | 0.0 | - |
|
544 |
+
| 21.3372 | 18350 | 0.0 | - |
|
545 |
+
| 21.3953 | 18400 | 0.0 | - |
|
546 |
+
| 21.4535 | 18450 | 0.0 | - |
|
547 |
+
| 21.5116 | 18500 | 0.0 | - |
|
548 |
+
| 21.5698 | 18550 | 0.0 | - |
|
549 |
+
| 21.6279 | 18600 | 0.0 | - |
|
550 |
+
| 21.6860 | 18650 | 0.0 | - |
|
551 |
+
| 21.7442 | 18700 | 0.0 | - |
|
552 |
+
| 21.8023 | 18750 | 0.0 | - |
|
553 |
+
| 21.8605 | 18800 | 0.0 | - |
|
554 |
+
| 21.9186 | 18850 | 0.0 | - |
|
555 |
+
| 21.9767 | 18900 | 0.0 | - |
|
556 |
+
| 22.0349 | 18950 | 0.0 | - |
|
557 |
+
| 22.0930 | 19000 | 0.0 | - |
|
558 |
+
| 22.1512 | 19050 | 0.0 | - |
|
559 |
+
| 22.2093 | 19100 | 0.0 | - |
|
560 |
+
| 22.2674 | 19150 | 0.0 | - |
|
561 |
+
| 22.3256 | 19200 | 0.0 | - |
|
562 |
+
| 22.3837 | 19250 | 0.0 | - |
|
563 |
+
| 22.4419 | 19300 | 0.0 | - |
|
564 |
+
| 22.5 | 19350 | 0.0 | - |
|
565 |
+
| 22.5581 | 19400 | 0.0 | - |
|
566 |
+
| 22.6163 | 19450 | 0.0 | - |
|
567 |
+
| 22.6744 | 19500 | 0.0 | - |
|
568 |
+
| 22.7326 | 19550 | 0.0001 | - |
|
569 |
+
| 22.7907 | 19600 | 0.0015 | - |
|
570 |
+
| 22.8488 | 19650 | 0.0 | - |
|
571 |
+
| 22.9070 | 19700 | 0.0 | - |
|
572 |
+
| 22.9651 | 19750 | 0.0 | - |
|
573 |
+
| 23.0233 | 19800 | 0.0 | - |
|
574 |
+
| 23.0814 | 19850 | 0.0 | - |
|
575 |
+
| 23.1395 | 19900 | 0.0 | - |
|
576 |
+
| 23.1977 | 19950 | 0.0 | - |
|
577 |
+
| 23.2558 | 20000 | 0.0 | - |
|
578 |
+
| 23.3140 | 20050 | 0.0 | - |
|
579 |
+
| 23.3721 | 20100 | 0.0 | - |
|
580 |
+
| 23.4302 | 20150 | 0.0 | - |
|
581 |
+
| 23.4884 | 20200 | 0.0 | - |
|
582 |
+
| 23.5465 | 20250 | 0.0 | - |
|
583 |
+
| 23.6047 | 20300 | 0.0 | - |
|
584 |
+
| 23.6628 | 20350 | 0.0 | - |
|
585 |
+
| 23.7209 | 20400 | 0.0 | - |
|
586 |
+
| 23.7791 | 20450 | 0.0 | - |
|
587 |
+
| 23.8372 | 20500 | 0.0 | - |
|
588 |
+
| 23.8953 | 20550 | 0.0 | - |
|
589 |
+
| 23.9535 | 20600 | 0.0 | - |
|
590 |
+
| 24.0116 | 20650 | 0.0 | - |
|
591 |
+
| 24.0698 | 20700 | 0.0 | - |
|
592 |
+
| 24.1279 | 20750 | 0.0 | - |
|
593 |
+
| 24.1860 | 20800 | 0.0 | - |
|
594 |
+
| 24.2442 | 20850 | 0.0 | - |
|
595 |
+
| 24.3023 | 20900 | 0.0 | - |
|
596 |
+
| 24.3605 | 20950 | 0.0 | - |
|
597 |
+
| 24.4186 | 21000 | 0.0 | - |
|
598 |
+
| 24.4767 | 21050 | 0.0 | - |
|
599 |
+
| 24.5349 | 21100 | 0.0 | - |
|
600 |
+
| 24.5930 | 21150 | 0.0 | - |
|
601 |
+
| 24.6512 | 21200 | 0.0 | - |
|
602 |
+
| 24.7093 | 21250 | 0.0 | - |
|
603 |
+
| 24.7674 | 21300 | 0.0 | - |
|
604 |
+
| 24.8256 | 21350 | 0.0 | - |
|
605 |
+
| 24.8837 | 21400 | 0.0 | - |
|
606 |
+
| 24.9419 | 21450 | 0.0 | - |
|
607 |
+
| 25.0 | 21500 | 0.0 | - |
|
608 |
+
| 25.0581 | 21550 | 0.0 | - |
|
609 |
+
| 25.1163 | 21600 | 0.0 | - |
|
610 |
+
| 25.1744 | 21650 | 0.0 | - |
|
611 |
+
| 25.2326 | 21700 | 0.0 | - |
|
612 |
+
| 25.2907 | 21750 | 0.0 | - |
|
613 |
+
| 25.3488 | 21800 | 0.0 | - |
|
614 |
+
| 25.4070 | 21850 | 0.0 | - |
|
615 |
+
| 25.4651 | 21900 | 0.0 | - |
|
616 |
+
| 25.5233 | 21950 | 0.0 | - |
|
617 |
+
| 25.5814 | 22000 | 0.0 | - |
|
618 |
+
| 25.6395 | 22050 | 0.0 | - |
|
619 |
+
| 25.6977 | 22100 | 0.0 | - |
|
620 |
+
| 25.7558 | 22150 | 0.0 | - |
|
621 |
+
| 25.8140 | 22200 | 0.0 | - |
|
622 |
+
| 25.8721 | 22250 | 0.0 | - |
|
623 |
+
| 25.9302 | 22300 | 0.0 | - |
|
624 |
+
| 25.9884 | 22350 | 0.0 | - |
|
625 |
+
| 26.0465 | 22400 | 0.0 | - |
|
626 |
+
| 26.1047 | 22450 | 0.0 | - |
|
627 |
+
| 26.1628 | 22500 | 0.0 | - |
|
628 |
+
| 26.2209 | 22550 | 0.0 | - |
|
629 |
+
| 26.2791 | 22600 | 0.0 | - |
|
630 |
+
| 26.3372 | 22650 | 0.0 | - |
|
631 |
+
| 26.3953 | 22700 | 0.0 | - |
|
632 |
+
| 26.4535 | 22750 | 0.0 | - |
|
633 |
+
| 26.5116 | 22800 | 0.0 | - |
|
634 |
+
| 26.5698 | 22850 | 0.0 | - |
|
635 |
+
| 26.6279 | 22900 | 0.0 | - |
|
636 |
+
| 26.6860 | 22950 | 0.0 | - |
|
637 |
+
| 26.7442 | 23000 | 0.0 | - |
|
638 |
+
| 26.8023 | 23050 | 0.0 | - |
|
639 |
+
| 26.8605 | 23100 | 0.0 | - |
|
640 |
+
| 26.9186 | 23150 | 0.0 | - |
|
641 |
+
| 26.9767 | 23200 | 0.0 | - |
|
642 |
+
| 27.0349 | 23250 | 0.0 | - |
|
643 |
+
| 27.0930 | 23300 | 0.0 | - |
|
644 |
+
| 27.1512 | 23350 | 0.0 | - |
|
645 |
+
| 27.2093 | 23400 | 0.0 | - |
|
646 |
+
| 27.2674 | 23450 | 0.0 | - |
|
647 |
+
| 27.3256 | 23500 | 0.0 | - |
|
648 |
+
| 27.3837 | 23550 | 0.0 | - |
|
649 |
+
| 27.4419 | 23600 | 0.0 | - |
|
650 |
+
| 27.5 | 23650 | 0.0 | - |
|
651 |
+
| 27.5581 | 23700 | 0.0 | - |
|
652 |
+
| 27.6163 | 23750 | 0.0 | - |
|
653 |
+
| 27.6744 | 23800 | 0.0 | - |
|
654 |
+
| 27.7326 | 23850 | 0.0 | - |
|
655 |
+
| 27.7907 | 23900 | 0.0 | - |
|
656 |
+
| 27.8488 | 23950 | 0.0 | - |
|
657 |
+
| 27.9070 | 24000 | 0.0 | - |
|
658 |
+
| 27.9651 | 24050 | 0.0 | - |
|
659 |
+
| 28.0233 | 24100 | 0.0 | - |
|
660 |
+
| 28.0814 | 24150 | 0.0 | - |
|
661 |
+
| 28.1395 | 24200 | 0.0 | - |
|
662 |
+
| 28.1977 | 24250 | 0.0 | - |
|
663 |
+
| 28.2558 | 24300 | 0.0 | - |
|
664 |
+
| 28.3140 | 24350 | 0.0 | - |
|
665 |
+
| 28.3721 | 24400 | 0.0 | - |
|
666 |
+
| 28.4302 | 24450 | 0.0 | - |
|
667 |
+
| 28.4884 | 24500 | 0.0 | - |
|
668 |
+
| 28.5465 | 24550 | 0.0 | - |
|
669 |
+
| 28.6047 | 24600 | 0.0 | - |
|
670 |
+
| 28.6628 | 24650 | 0.0 | - |
|
671 |
+
| 28.7209 | 24700 | 0.0 | - |
|
672 |
+
| 28.7791 | 24750 | 0.0 | - |
|
673 |
+
| 28.8372 | 24800 | 0.0 | - |
|
674 |
+
| 28.8953 | 24850 | 0.0 | - |
|
675 |
+
| 28.9535 | 24900 | 0.0 | - |
|
676 |
+
| 29.0116 | 24950 | 0.0 | - |
|
677 |
+
| 29.0698 | 25000 | 0.0 | - |
|
678 |
+
| 29.1279 | 25050 | 0.0 | - |
|
679 |
+
| 29.1860 | 25100 | 0.0 | - |
|
680 |
+
| 29.2442 | 25150 | 0.0 | - |
|
681 |
+
| 29.3023 | 25200 | 0.0 | - |
|
682 |
+
| 29.3605 | 25250 | 0.0 | - |
|
683 |
+
| 29.4186 | 25300 | 0.0 | - |
|
684 |
+
| 29.4767 | 25350 | 0.0 | - |
|
685 |
+
| 29.5349 | 25400 | 0.0 | - |
|
686 |
+
| 29.5930 | 25450 | 0.0 | - |
|
687 |
+
| 29.6512 | 25500 | 0.0 | - |
|
688 |
+
| 29.7093 | 25550 | 0.0 | - |
|
689 |
+
| 29.7674 | 25600 | 0.0 | - |
|
690 |
+
| 29.8256 | 25650 | 0.0 | - |
|
691 |
+
| 29.8837 | 25700 | 0.0 | - |
|
692 |
+
| 29.9419 | 25750 | 0.0 | - |
|
693 |
+
| 30.0 | 25800 | 0.0 | - |
|
694 |
+
|
695 |
+
### Framework Versions
|
696 |
+
- Python: 3.10.12
|
697 |
+
- SetFit: 1.1.0
|
698 |
+
- Sentence Transformers: 3.3.1
|
699 |
+
- Transformers: 4.44.2
|
700 |
+
- PyTorch: 2.2.0a0+81ea7a4
|
701 |
+
- Datasets: 3.2.0
|
702 |
+
- Tokenizers: 0.19.1
|
703 |
+
|
704 |
+
## Citation
|
705 |
+
|
706 |
+
### BibTeX
|
707 |
+
```bibtex
|
708 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
709 |
+
doi = {10.48550/ARXIV.2209.11055},
|
710 |
+
url = {https://arxiv.org/abs/2209.11055},
|
711 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
712 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
713 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
714 |
+
publisher = {arXiv},
|
715 |
+
year = {2022},
|
716 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
717 |
+
}
|
718 |
+
```
|
719 |
+
|
720 |
+
<!--
|
721 |
+
## Glossary
|
722 |
+
|
723 |
+
*Clearly define terms in order to be accessible across audiences.*
|
724 |
+
-->
|
725 |
+
|
726 |
+
<!--
|
727 |
+
## Model Card Authors
|
728 |
+
|
729 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
730 |
+
-->
|
731 |
+
|
732 |
+
<!--
|
733 |
+
## Model Card Contact
|
734 |
+
|
735 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
736 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mini1013/master_domain",
|
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 |
+
"normalize_embeddings": false,
|
3 |
+
"labels": null
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dcb8efd08ea3cf612a4d7b7cce68cf7dbe481ee638e6c9e9afa6064141052ee
|
3 |
+
size 442494816
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65e0feaf53cda8ed7dd131f4f38badd1cf11abd01c893be6d20f606fa6d32e96
|
3 |
+
size 68607
|
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
|
|