Instructions to use kisti/korscideberta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kisti/korscideberta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="kisti/korscideberta")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("kisti/korscideberta") model = AutoModelForMaskedLM.from_pretrained("kisti/korscideberta") - Notebooks
- Google Colab
- Kaggle
Upload korscideberta-abstractcls.ipynb
Browse files
korscideberta-abstractcls.ipynb
CHANGED
|
@@ -47,7 +47,8 @@
|
|
| 47 |
"source": [
|
| 48 |
"'''\n",
|
| 49 |
"#[ํ์]๋ฆฌ๋
์ค ํฐ๋ฏธ๋์์ ๋ณธ ์ฝ๋ ๋ฐ ํ ํฌ๋์ด์ ๋ค์ด๋ก๋\n",
|
| 50 |
-
"
|
|
|
|
| 51 |
"\n",
|
| 52 |
"#[ํ์]๋ผ์ด๋ธ๋ฌ๋ฆฌ ์ค์น(Mecab ๋ฑ ์์ธํ ์ค์น ๋ฐฉ๋ฒ์ README ์ฐธ์กฐ)\n",
|
| 53 |
"!apt install git-lfs\n",
|
|
@@ -177,7 +178,7 @@
|
|
| 177 |
"#ํ ํฐ ์์: hf_jRjLZcSBibYHwUaTjiNUEeoJlFxhFkGM\n",
|
| 178 |
"\n",
|
| 179 |
"#model_repository = \"kkmkorea/checkpoint25000\"\n",
|
| 180 |
-
"model_repository = \"
|
| 181 |
"from transformers import AutoTokenizer\n",
|
| 182 |
"from tokenization_korscideberta import DebertaV2Tokenizer\n",
|
| 183 |
"tokenizer = DebertaV2Tokenizer.from_pretrained(model_repository)\n",
|
|
|
|
| 47 |
"source": [
|
| 48 |
"'''\n",
|
| 49 |
"#[ํ์]๋ฆฌ๋
์ค ํฐ๋ฏธ๋์์ ๋ณธ ์ฝ๋ ๋ฐ ํ ํฌ๋์ด์ ๋ค์ด๋ก๋\n",
|
| 50 |
+
"#git clone https://huggingface.co/kisti/korscideberta\n",
|
| 51 |
+
"#cd korscideberta\n",
|
| 52 |
"\n",
|
| 53 |
"#[ํ์]๋ผ์ด๋ธ๋ฌ๋ฆฌ ์ค์น(Mecab ๋ฑ ์์ธํ ์ค์น ๋ฐฉ๋ฒ์ README ์ฐธ์กฐ)\n",
|
| 54 |
"!apt install git-lfs\n",
|
|
|
|
| 178 |
"#ํ ํฐ ์์: hf_jRjLZcSBibYHwUaTjiNUEeoJlFxhFkGM\n",
|
| 179 |
"\n",
|
| 180 |
"#model_repository = \"kkmkorea/checkpoint25000\"\n",
|
| 181 |
+
"model_repository = \"kisti/korscideberta\" #Huggingface ๋ชจ๋ธ๋ช
์ค์ \n",
|
| 182 |
"from transformers import AutoTokenizer\n",
|
| 183 |
"from tokenization_korscideberta import DebertaV2Tokenizer\n",
|
| 184 |
"tokenizer = DebertaV2Tokenizer.from_pretrained(model_repository)\n",
|