Instructions to use alaggung/bart-r3f with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alaggung/bart-r3f with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("summarization", model="alaggung/bart-r3f")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("alaggung/bart-r3f") model = AutoModelForSeq2SeqLM.from_pretrained("alaggung/bart-r3f", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from alaggung/bart-r3f: direct link, hf CLI and curl.
- Browser
- Download file 879 Bytes
-
https://huggingface.co/alaggung/bart-r3f/resolve/main/README.md
- Command line
-
hf download hf://alaggung/bart-r3f/README.md
-
curl -L -o README.md https://huggingface.co/alaggung/bart-r3f/resolve/main/README.md
879 Bytes
metadata
language:
- ko
tags:
- summarization
widget:
- text: >-
[BOS]밥 ㄱ?[SEP]고고고고 뭐 먹을까?[SEP]어제 김치찌개 먹어서 한식말고 딴 거[SEP]그럼 돈까스 어때?[SEP]오 좋다
1시 학관 앞으로 오셈[SEP]ㅇㅋ[EOS]
inference:
parameters:
max_length: 64
top_k: 5
BART R3F
[2021 훈민정음 한국어 음성•자연어 인공지능 경진대회] 대화요약 부문 알라꿍달라꿍 팀의 대화요약 학습 샘플 모델을 공유합니다.
bart-pretrained 모델에 2021-dialogue-summary-competition 레포지토리의 R3F를 적용해 대화요약 Task를 학습한 모델입니다.
데이터는 AIHub 한국어 대화요약 데이터를 사용하였습니다.