How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-classification", model="ayarnte/IRM_Arc")
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("ayarnte/IRM_Arc")
model = AutoModelForSequenceClassification.from_pretrained("ayarnte/IRM_Arc")
Quick Links

IRM High Ver

DeBERTa-v3-large をベースにした Idea Reward Model(不確実性回帰 + Isotonic 校正)。 入力: タイトル + アブストラクト → 回帰スコア(μ)と 0–1 の報酬にマッピング。

Downloads last month
2
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support