Instructions to use lIlBrother/ko-answerable with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lIlBrother/ko-answerable with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="lIlBrother/ko-answerable")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("lIlBrother/ko-answerable") model = AutoModelForSequenceClassification.from_pretrained("lIlBrother/ko-answerable") - Notebooks
- Google Colab
- Kaggle
| language: | |
| - ko | |
| metrics: | |
| - accuracy | |
| pipeline_tag: text-classification | |
| # Optional. Add this if you want to encode your eval results in a structured way. | |
| model-index: | |
| - name: ko-answerable | |
| results: | |
| - task: | |
| type: text-classification # Required. Example: automatic-speech-recognition | |
| name: text-classification # Optional. Example: Speech Recognition | |
| metrics: | |
| - type: eval_accuracy | |
| value: 0.892 | |
| name: eval_accuracy | |
| verified: false | |
| - type: test_accuracy | |
| value: 0.837 | |
| name: test_accuracy | |
| verified: false | |
| # ko-answerable: Passage์ Question์ด ๋ต๋ณ์ ํ ์ ์๋๊ฐ?์ 2์ง ๋ถ๋ฅ | |
| ## Model Details | |
| SelfCheckGPT์ Answerable model์ ๊ฐ๋ช ๋ฐ์ ์ ์ํ๊ฒ ๋์์ต๋๋ค. (https://arxiv.org/abs/2303.08896) | |
| [monologg/kobigbird-bert-base](https://huggingface.co/monologg/kobigbird-bert-base) ๋ชจ๋ธ์ ์ฌ์ฉํ์ฌ [BigBirdForSequenceClassification](https://huggingface.co/docs/transformers/v4.33.0/en/model_doc/big_bird#transformers.BigBirdForSequenceClassification) ์ผ๋ก Fine-Tune ๋์์ต๋๋ค | |
| Max Seq Len: 4096 | |
| Input Text Style: \<BOS\>Question\<SEP>Title\<SEP\>Passage\<EOS\> | |
| Return: 1: ์๋ต ์์, 0: ์๋ต ๊ฐ๋ฅ (sigmoid score ์ฌ์ฉ ๊ฐ๋ฅ) | |
| ์ฌ์ฉ๋ ๋ฐ์ดํฐ์ (ํด๋น ๋ฐ์ดํฐ์ ์์ 'is_impossible'์ ๊ธฐ์ค์ผ๋ก 50:50์ผ๋ก ๋๋ค ์ถ์ถ(0,1 ๋น์ค์ด ๋ง๋๋ก)) | |
| 1. KLUE | |
| 2. AIHub-๋์์๋ฃ ๊ธฐ๊ณ๋ ํด | |
| 3. AIHub-๋ด์ค ๊ธฐ์ฌ ๊ธฐ๊ณ๋ ํด ๋ฐ์ดํฐ | |
| 4. AIHub-ํ์ ๋ฌธ์ ๋์ ๊ธฐ๊ณ๋ ํด ๋ฐ์ดํฐ | |
| 5. ํ๊ธฐ๋ฐ ์ง์์๋ต ๋ฐ์ดํฐ (๋งคํ๋์๊ฒ ๊ฐ์ธ์ ์ผ๋ก ๋ฐ์) | |
| `AIHub-๊ธฐ๊ณ๋ ํด` ๋ฐ์ดํฐ๋ ์กด์ฌํ๋, ๋ฐ์ดํฐ ์ ์ฒ๋ฆฌํ๊ธฐ ๊ตฌ์กฐ๊ฐ ์ข ๋ณต์กํ๊ฒ ๋ฌ๋ผ์ ์ ์ธํจ. | |
| ์์ธก ์๊ฐ: ๊ฑด๋น ํ๊ท 0.05์ด ์ด๋ด (RTX 3090 ์ฌ์ฉ) | |
| ์ฌ์ฉ GPU MEM: About 20GB (Seq๊ฐ ๊ธธ๋ฉด ๋ง์ด ๋จน์) | |