Measured result
Mind2Web, MindAct protocol, cross-domain split (websites from domains never seen in training), 200 steps:
Table with columns: model, step success, element accuracy, operation F1| model | step success | element accuracy | operation F1 |
|---|
| AUBIN-31B-Web | 45.0 | 49.0 | 0.890 |
| AUBIN-12B-Web | 43.5 | | |
Training: 420 steps on the Mind2Web train split from the Gemma-4-31B base (4-bit, one free Kaggle T4 session). The step with the best score on a held-out dev split (step 300) was selected before testing. Result file: reports/w31s_test_domain.json.
Use
from aubin import AubinOmniomni = AubinOmni.from_hub("emrevrg/AUBIN-Omni", size="31B")omni.web_step("Book a flight from New York to Paris", {"n1": "<input placeholder='From'>", "n2": "<a>Hotels</a>"})
♥ Help AUBIN get seen
On Hugging Face, likes decide what people discover. Big labs have marketing teams; AUBIN has one 17-year-old student and measured results.
If AUBIN is useful, interesting or just impressive to you, press ♥ Like at the top of this page and on AUBIN-Omni, AUBIN-31B and AUBIN-12B, then share it with one person who builds with AI.
Every like helps an independent, open, honestly measured model get discovered.
🇹🇷 Beğenin, AUBIN'in görünür olmasını sağlar: sayfanın üstündeki ♥ Like'a basarak destek ol ve bir arkadaşına gönder.
Support Norovox
Norovox is built by one 17-year-old high school student in Türkiye: no company, no sponsor, no budget.
Every model on this page was trained on free GPU quotas that run out within days. When they run out, training stops
halfway and the next, stronger version has to wait, sometimes for a week.
Your support goes directly into GPU time. Even a small contribution lets a training run finish instead of stopping,
and helps the Nythos, N1, AUBIN and Norovox Embed models get better faster. Supporters are credited in the model cards
and get early access to new releases.
Contact: zgremre@gmail.com · emrevrgdev@gmail.com
🇹🇷 Norovox'u Türkiye'de 17 yaşında bir lise öğrencisi tek başına geliştiriyor: şirket yok, sponsor yok, bütçe yok. Buradaki modellerin hepsi birkaç günde biten ücretsiz GPU kotalarıyla eğitildi; kota bitince eğitim yarıda kalıyor ve daha güçlü sürüm bekliyor. Desteğin doğrudan GPU süresine gider; küçük bir katkı bile bir eğitimin yarıda kalmadan tamamlanmasını sağlar. Destekçiler model kartlarında anılır ve yeni sürümlere erken erişir. İletişim: zgremre@gmail.com · emrevrgdev@gmail.com
Built with Claude Opus 5.5 and GPT-5.6 Sol; because of OpenAI usage limits, the final stretch was completed with Claude Opus 5.5.
License: Apache-2.0 (adapters and code). Base models: Google Gemma 4 (Apache-2.0).