Downloads · 30 days
0
nagisanzeninz/nagi-t4-m2p-v0
nagi-t4-m2p-v0 is a machine learning model from nagisanzeninz. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
System One typed-decision model (choice / score / noul) — M2' dual encoder + option tower.
Downloads · 30 days
0
Access
Public
Updated Sep 23, 2026
Repo size
42.2 GB
Likes
0
Public
Click a slice to open those files.
.pt42.2 GB · 100%
From the Hugging Face model README
System One typed-decision model (choice / score / noul) — M2' dual encoder + option tower.
| Nagi T4 | Laya | Jev | |
|---|---|---|---|
| hard | 0.481 | ~0.35 | 0.773 |
| ECE raw | 0.070 | 0.081 | 0.121 |
| p50 | 9.2ms | 33ms | 501ms |
Beats Laya on LTO + latency. 55× faster than Jev API. Honest gap: LTO 0.48 vs Jev 0.77. Domain FT (prior): Banking77 0.942. Train: 17k rows / 643 schemas / H100 BF16 3ep.