Task
Text Classification
Q
saiteki-kai/QA-DeBERTa-IGPooling-binary
Text Classification·saiteki-kai· 74
transformers
mit
Text Classification
439.3M params
dataset:beavertailsbase_model:microsoft/deberta-v3-largebase_model:finetune:microsoft/deberta-v3-largelicense:mit
This model is a fine-tuned version of microsoft/deberta-v3-large on the saiteki-kai/Beavertails-it dataset. It achieves the following results on the evaluation set: - Loss: 0.4138 - Accuracy: 0.8652 - Unsafe Precision: 0.8925 - Unsafe Recall: 0.8616 - Unsafe F1: 0.8768 - Unsafe Fpr: 0.1302 - Unsafe Aucpr: 0.9567 - Safe Precision: 0.8336 - Safe Recall: 0.8698 - Safe F1: 0.8513 - Safe Fpr: 0.1384 -
# pull & run locally
pip install mlforge-sdk && mlforge pull saiteki-kai/QA-DeBERTa-IGPooling-binary
pip install mlforge-sdk && mlforge pull saiteki-kai/QA-DeBERTa-IGPooling-binary
Model details
Provider
saiteki-kai
Framework
transformers
Parameters
439.3M
Size
9.8 GB
License
mit
Downloads
74
Updated
2026-06-24
About saiteki-kai/QA-DeBERTa-IGPooling-binary
This model is a fine-tuned version of microsoft/deberta-v3-large on the saiteki-kai/Beavertails-it dataset. It achieves the following results on the evaluation set: - Loss: 0.4138 - Accuracy: 0.8652 - Unsafe Precision: 0.8925 - Unsafe Recall: 0.8616 - Unsafe F1: 0.8768 - Unsafe Fpr: 0.1302 - Unsafe Aucpr: 0.9567 - Safe Precision: 0.8336 - Safe Recall: 0.8698 - Safe F1: 0.8513 - Safe Fpr: 0.1384 - Safe Aucpr: 0.9230
Related Text Classification
B
BAAI/bge-reranker-v2-m3
16.2M 1.1K
🤗 HF
F
ProsusAI/finbert
7.6M 1.2K
🤗 HF
B
BAAI/bge-reranker-base
4.1M 238
🤗 HF
T
cardiffnlp/twitter-roberta-base-sentiment-latest
3.9M 813
🤗 HF
D
distilbert/distilbert-base-uncased-finetuned-sst-2-english
3.6M 910
🤗 HF
T
trl-internal-testing/tiny-Qwen2ForSequenceClassification-2.5
1.5M 1
🤗 HF