Up to date
C-Tianyu Not declared out 38 days ago
Verified 2026-10-25 Rank #0 in Decision models · score 0 method v1 Sources 3 Downloads 30d 2.4k · #575 of 619 tracked
Picked by rule from 1 tracked piece: the lab's own post, the most shared, a field report, the latest.
nanojev is a hypothetical reconstruction of TypeSafe's closed Jev decision model, designed as the smallest working version of what black-box probing suggests.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 5 Spaces.
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2026-09-17), amber triangles are 1 dated article (each links to it), grey ticks are repo commits.
6 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported Basic | 128/128 | — | model author | 2026-10-07 |
| author-reported Maze | 4/10 | — | model author | 2026-10-07 |
| author-reported Predict Position | 27/128 | — | model author | 2026-10-07 |
| author-reported Snake | 8/8 | — | model author | 2026-10-07 |
NanoJev is a 0.6B decision model fine-tuned from the Qwen3-0.6B backbone.[1][2] The model returns action distributions for tasks including Maze, Snake, and ViZDoom Basic.[1] It utilizes a shared backbone with an attention-based Choice head to score candidate sets.[3]
Generated 2026-10-07 15:19 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in Decision models
| Library | pytorch |
|---|---|
| MoE | no |
| Languages | en |
| License | Not declared |
| Hub snapshot | 2026-10-25 |
| How it was made | decision head on Qwen3-0.6B |
|---|---|
| Lineage bucket | F - fine-tune of an open model (public/synthetic data) |
| Lineage evidence | HF base_model + tracker |
| Base model | Qwen/Qwen3-0.6B |
| Hosted price (input) | self-hosted/M |
| Source | https://huggingface.co/C-Tianyu/NanoJev |
Base model: Qwen/Qwen3-0.6B
finetune: 6
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| zerodegress/NanoJev-mlx-4bit | finetune | mlx | — | — | — | zerodegress | 1 | 575 |
| zerodegress/NanoJev-bf16 | finetune | -bf16 | — | — | — | zerodegress | 0 | 133 |
| candypunk/NanoJev-Web | finetune | — | — | — | other | candypunk | 1 | 46 |
| yannelli/nanojev-code-review-decisions | finetune | — | — | — | apache-2.0 | yannelli | 1 | 40 |
| FluidInference/nanojev-coreml | finetune | — | — | — | — | FluidInference | 0 | 13 |
| jayzou3773/ra2-nanojev-sft-epoch2 | finetune | — | — | — | — | jayzou3773 | 0 | 13 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:44 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:19 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
