cetusian/test
Updated
🏗️ Building on HF
Madalin Tatarciuc
cetusian
AI & ML interests
instinctively gravitating toward the frontier where intelligence meets constraints.
Recent Activity
liked a model about 12 hours ago
Qwen/Qwen3.5-2B liked a dataset about 12 hours ago
anthonytec2/OctoSense posted an update 3 days ago
most labs won't bother teaching a small model to write and think in real romanian. no invented words, no english leaking in mid-sentence, diacritics intact.
we did.
surogate 3.5 is out. 2B and 4B, apache 2.0. invented word-forms cut from 4 per 1k down to ~1.5, and it reasons in the language you prompt it in, every time.
intelligence should speak your language too.
the models:
https://huggingface.co/surogate/Surogate-3.5-4B
https://huggingface.co/surogate/Surogate-3.5-2BOrganizations
cetusian/pocket-atlas-0.8b
Text Generation • 0.9B • Updated • 61
cetusian/distilbert-ner-furniture-names-v3
Token Classification • Updated • 4
cetusian/Autonomous-Taxi
Reinforcement Learning • Updated
cetusian/q-FrozenLake-v1-4x4-noSlippery
Reinforcement Learning • Updated
cetusian/PPO-Huggy
Reinforcement Learning • Updated • 7
cetusian/PPO-Lunar-Lander
Reinforcement Learning • Updated