Downloads · 30 days
0
SpanCalib-VLM-Multimodal
amanuelbyte/SpanCalib-VLM-Multimodal
SpanCalib-VLM-Multimodal is a machine learning model from amanuelbyte. 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.
Token-level hallucination detection: XLM-RoBERTa-Large + SigLIP-2 cross-attention fusion. Best Val Pearson: 0.3688 (Epoch 2/5)
Access
Public
Updated Jul 25, 2026
Repo size
2.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.6 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026
- SHA
- 2b881994
Model card
From the Hugging Face model README
SpanCalib-VLM Multimodal
Token-level hallucination detection: XLM-RoBERTa-Large + SigLIP-2 cross-attention fusion. Best Val Pearson: 0.3688 (Epoch 2/5)
- License
- mit
- Languages
- en
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026