Buckets:
| language: | |
| - en | |
| base_model: Qwen/Qwen3-0.6B | |
| library_name: pytorch | |
| tags: | |
| - nanojev | |
| - decision-model | |
| - reinforcement-learning-environment | |
| - supervised-fine-tuning | |
| - maze | |
| - snake | |
| - vizdoom | |
| # NanoJev — A nano replica of Jev | |
| One 0.6B model returns action distributions for Maze, Snake, ViZDoom Basic and | |
| Predict Position. This public release contains the current unified | |
| step-400 model, its exact training initialization and the full inference source. | |
| [Jev](https://typesafe.ai/blog/introducing-system-one-models-and-jev) inspired the | |
| state, question and candidate-set interface. | |
| Each candidate is encoded with its state and question. A shared Qwen3-0.6B | |
| backbone, end-of-sequence representations and an attention-based Choice head | |
| score the offered set. Softmax returns all candidate probabilities together, | |
| without output-token decoding. Boolean and ordered-score request types remain | |
| available through the same structured interface. | |
| | Matched test task | NanoJev | Jev | Untuned Qwen | | |
| |---|---:|---:|---:| | |
| | Maze | 4/10 | 7/10 | 2/10 | | |
| | Snake | 8/8 | 8/8 | 0/8 | | |
| | Basic | 128/128 | 56/128 | 56/128 | | |
| | Predict Position | 27/128 | 11/128 | 11/128 | | |
| All systems share the recorded structured observation interface, frozen cases, | |
| controller epsilon 0.1 and sampling seed 17. Full test and OOD reports, source | |
| trajectories and independent replay checks are in the linked dataset. The hard | |
| 50x50 Maze and 12x12 Snake demonstrations are a separately recorded showcase | |
| using common code planners: current NanoJev reaches the maze goal in 225 attempts | |
| and collects 30 food items while surviving all 256 Snake steps. | |
| ## Load the model | |
| [Complete mixed dataset and recordings](https://huggingface.co/datasets/C-Tianyu/NanoJev-Data) | |
| · [Training recipe](TRAINING_RECIPE.md) | |
| · [File hashes](SHA256_MANIFEST.json) | |
| The release is available without authentication. | |
| The root directory is the current complete checkpoint bundle; it is loaded by | |
| NanoJev's `DecisionPredictor`. | |
| ```python | |
| import sys | |
| from huggingface_hub import snapshot_download | |
| path = snapshot_download("C-Tianyu/NanoJev", revision="unified-games-v1", | |
| token=False, allow_patterns=["best.safetensors", "config.json", | |
| "backbone_config/*", "tokenizer/*", "source/*"]) | |
| sys.path.insert(0, path + "/source/scripts") | |
| from predict_toy_decisions import DecisionPredictor | |
| model = DecisionPredictor(path, device_name="cuda:0", precision="bf16", | |
| disable_native_triton=True) | |
| request = {"states": [{"id": "example", "state": "The target is left of the aim.", | |
| "questions": {"action": {"type": "choice", "instructions": "Choose the next action.", | |
| "criteria": {"left": "Move the aim left.", "right": "Move the aim right.", | |
| "shoot": "Fire.", "noop": "Wait."}}}}]} | |
| answer = model.predict(request) | |
| print(answer) | |
| ``` | |
| The saved format contains `best.safetensors`, `config.json`, `backbone_config/` | |
| and `tokenizer/`, plus the original training audits. It is the project's decision | |
| model format. The base revision is | |
| `Qwen/Qwen3-0.6B@c1899de289a04d12100db370d81485cdf75e47ca`. | |
| Training uses mixed-task supervised cross entropy. Predict Position action | |
| supervision comes from the released Sonic Doom visual expert. The existing | |
| Maze, Snake and Basic data remain in their original splits. Four matched runs | |
| compare hard/soft PP targets and two learning rates; development performance | |
| selects `hard_lr1e5` at step 400. The selected weight SHA256 is | |
| `f68c47d66998231b86b7e91b4ed5e82ae23acf104c8b7cd6d165c3ac7b7ffe1b`. The full original 15-file bundle is preserved. | |
| Source code carries the included MIT license; the Qwen base model retains its | |
| upstream license. Model and data snapshots are published as `unified-games-v1`. | |
| ## Release history | |
| The inference download above includes the current model and source. The full training | |
| package also includes `training_initialization/`; use the manifest allowlist in | |
| [the recipe](TRAINING_RECIPE.md) to download all current files. | |
| The current release is verified by `SHA256_MANIFEST.json`. Retained | |
| `MODEL_MANIFEST.json`, `GAMES_MODEL_MANIFEST.json`, `stage1/` and `variants/` | |
| belong to earlier releases. The prior root snapshot remains available at | |
| [`legacy-before-unified-games-v1`](https://huggingface.co/C-Tianyu/NanoJev/tree/legacy-before-unified-games-v1). | |
Xet Storage Details
- Size:
- 4.36 kB
- Xet hash:
- 2e2aefe1bf5982d5de20c93c7d4e793e995a3921e7f6ab398d253e715f27eda6
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.