Organization repository on GitHub
⚡ 适合中国宝宝的 Jev 入门教程｜手把手带你了解关于 Jev 的一切——Jupyter Notebook 轻松实验，从三种问题原语到 18 篇实战配方、语音智能家居、模型评测与本地微调，全面掌握 System One 判断模型的开发范式
- Forks
- 39
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
CommunityJev Tools & CLIs
Jev Docs Zh
Chinese Jev Cookbook with runnable Jupyter notebooks covering the three question primitives, 18 official recipes, a voice-driven 3D smart home, eval discipline, and local Laya fine-tuning.
- Stars
- 335
- Language
- Python
- Published by
- Community
- Author
- Bald0Wang
- Last verified
- Oct 2026
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- Python
Highlights
- Teaches Choice, Score, and Noul with one-thing-per-question discipline across eleven runnable chapters.
- Runs notebooks with offline examples keyless, then the same code against the live model with a key.
- Includes 18 official recipe reproductions plus a voice-driven 3D smart home and 12 runnable app projects.
- Covers honest four-dimension eval discipline and an RLCD pipeline for a local Laya service.
Watch out
Community Chinese translation with the English docs as the authoritative source; probabilities, latency, tokens, and costs come from re-runnable outputs with manual demo data labeled. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
Basic Python and Jupyter use is enough with no machine-learning background. Offline examples run with no key to learn every code path, and the same code connects to the live model once you configure a key.
It adds a guided Chinese path: eleven chapters from primitives and patterns through 18 recipe reproductions with engineering notes, plus a translated docs site and a file knowledge base. The English original remains authoritative.
Lesson probabilities, latency, tokens, and costs come from outputs you can rerun, with hand-made demo data explicitly labeled. The eval chapter enforces no retries, no fallbacks, and budget accounting over its question set.
One chapter gates Pi tool calls and replays DSH decision collaboration, and another walks RLCD fine-tuning on a Chinese dataset through to a local Jev-compatible service.
Python 3.10 or newer and Jupyter. Clone the repository, enter main/ and run ./setup_env.sh to build the environment. A TYPESAFE_API_KEY is optional for the offline examples and free to register when you want the same code to hit the live model.
The repository's original content is CC BY-NC-SA 4.0, so it is non-commercial and share-alike. Third-party projects it collects, such as jev-games, the JevBench question set and knowledge-base snapshots, stay under their own licenses.
The Datawhale community project is maintained by Bald0Wang as project lead with lzdFeiFei, Fyuan0206, Micheal024 and yeyeyeyeeeee. Bugs and suggestions go through GitHub Issues and Discussions, and experiments are contributed as pull requests.
More Jev resources like this
34GitHub stars
Pure-HTTP automation for the TypeSafe register, magic-link login, onboarding, and API-key creation flow, with pluggable temp-mail backends, concurrent batch runs, and key verification exports.
Jev Tools & CLIs#community#awesomejev#catalog-import
Community
2951461586/Jev-Register-ToolPython
2951461586/Jev-Register-ToolPython36GitHub stars
Python toolkit plus 0.8B multimodal model that takes a message, document, or image and returns calibrated choice, yes/no, and score answers in one forward pass for local decision workloads.
Jev Tools & CLIs#community#awesomejev#catalog-import
Community
PsiACE/dohnutsPython
PsiACE/dohnutsPython39GitHub stars
Video tool where Jev scores subtitle segments and code assembles a short highlights cut plus a de-watered full cut with timestamped summaries.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
cclank/jevclipPython
cclank/jevclipPython30GitHub stars
Forkable weekday radar that asks Jev one yes-or-no question per interest over each new arXiv announcement and publishes a page plus RSS feed.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
Eliot5566/JEV-Paper-RadarPython
Eliot5566/JEV-Paper-RadarPython38GitHub stars
Async supervisory layer for Hermes Agent that locks Definitions of Done, proves mechanical criteria locally, and calls Jev only for unresolved semantic checks under a token budget.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
keeltrace/hermes-nervePython
keeltrace/hermes-nervePython15GitHub stars
Two-tier decision engine pairing a 22.6M-parameter MiniLM encoder on the Apple Neural Engine with the on-device Apple Foundation Model as fallback for uncertain inputs.
Jev Tools & CLIs#community#awesomejev#catalog-import
Community
kerryrm/systemANEPython
kerryrm/systemANEPythonFrom the Jev guides
Original write-ups on what this entry is for.
The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Jev Tools & CLIs#classification#email#security
Read article
From the Jev community
Posts from builders shipping with Jev right now.