NanoJev
A 0.6B replica of the System One idea trained on game environments. A Qwen3-0.6B backbone with an attention-based Choice head that scores a dynamic candidate set for Maze, Snake, ViZDoom and position prediction, shipped with its full training pipeline.
Reported game results: Snake 8/8, ViZDoom Basic 128/128 (Jev 56/128), Maze 4/10 (Jev 7/10). The code is MIT; the Qwen base keeps its own licence. The repository holds 212 files across stage checkpoints and variants; the entry here points at the best checkpoint and tokenizer.
What it decides
- choice — picks one option from a set
- noul — answers a yes/no question with one calibrated probability
- score — places the input on an ordered scale
At a glance
| Parameters | 0.6B |
| Base model | qwen/qwen3-0.6b |
| Maker | TianyuCodings |
| Released | 2026-09-17 |
| License | mit |
Get the weights
pip install systemonemodels
systemone pull tianyu-codings/nanojev
The files are served from the maker's Hugging Face repository, C-Tianyu/NanoJev, and verified against the checksums recorded here.
Read more
This page was opened by System One for TianyuCodings, who can claim the organisation and take it over at any time.