Instructions to use A-Funakoshi/bert-wrime-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use A-Funakoshi/bert-wrime-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="A-Funakoshi/bert-wrime-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("A-Funakoshi/bert-wrime-base") model = AutoModelForSequenceClassification.from_pretrained("A-Funakoshi/bert-wrime-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from A-Funakoshi/bert-wrime-base: direct link, hf CLI and curl.
- Browser
- Download file 511 Bytes
-
https://huggingface.co/A-Funakoshi/bert-wrime-base/resolve/main/README.md
- Command line
-
hf download hf://A-Funakoshi/bert-wrime-base/README.md
-
curl -L -o README.md https://huggingface.co/A-Funakoshi/bert-wrime-base/resolve/main/README.md
511 Bytes
metadata
language:
- ja
metrics:
- accuracy
- f1
wrime-sentimentデータセットをbertベースのモデルでfinetuningしたもの
- ベースモデル:cl-tohoku/bert-base-japanese-whole-word-masking
- データセット:llm-book/wrime-sentiment
- 学習率スケジュールタイプ(lr_scheduler_type): constant
- 学習率(learning rate): 2e-5
- 勾配累積ステップ(gradient_accumulation_steps): なし
- 正則化(weight_decay): なし
- Epoch: 100
- EarlyStopping: early_stopping_patience=3