Downloads · 30 days
14
32% of all-time downloads
regressor-entropy
KevinDavidHayes/regressor-entropy
regressor-entropy is a machine learning model from KevinDavidHayes. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Predicts the attention entropy of a text sample - how spread out vs focused the attention patterns are.
All-time downloads
44
Public
Parameters
150M
5.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt3.6 GB · 60%
At a glance
- License
- mit
- Model type
- modernbert
- Access
- Public
- Created
- Jan 3, 2026
- Updated
- Jan 3, 2026
- SHA
- 565f0d73
Base models
Model card
From the Hugging Face model README
Long-Context Attention Regressor (Entropy)
Predicts the attention entropy of a text sample - how spread out vs focused the attention patterns are.
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
model = AutoModelForSequenceClassification.from_pretrained("KevinDavidHayes/regressor-entropy")
tokenizer = AutoTokenizer.from_pretrained("KevinDavidHayes/regressor-entropy")
text = "Your text here..."
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=8192)
with torch.no_grad():
score = model(**inputs).logits.item()
# Higher score = more spread attention (uses more context)
Training
- Base model: ModernBERT-base (8K context)
- Target: Normalized attention entropy
- Labels: Generated using Qwen2.5-7B-Instruct attention analysis at layer 14
Citation
Part of research on attention-based data filtering for long-context pretraining.
- Type
- modernbert
- License
- mit
- Languages
- en
- Created
- Jan 3, 2026
- Updated
- Jan 3, 2026