AI UP LAB面向任务的 AI 实践资源AI resources for real tasks
收藏Saved
更多More
StarStar
kouhxp kouhxp 官方 Official 社区 showcase Community showcase

Gutsy：本机 CPU 可跑的 0.8B Jev 兼容决策模型 Gutsy: 0.8B Jev-compatible decision model for local CPU

Gutsy: 0.8B Jev-compatible decision model for local CPU

kouhxp 开源的 gutsy-0.8b（v0.4）：把 Qwen3.5-0.8B 微调成决策模型，不生成自由文本。你送一段状态（文本或 JSON）和 typed questions（yes/no、choice、score），它为每个选项返回校准概率；choice / score 还带 reject。运行时 gutsy-inference 走 llama.cpp，默认可在普通 CPU 上起本地 HTTP；接口刻意对齐 Jev / System One（`/v1/systemone` 等），现有客户端多半只换 base URL。权重在 Hugging Face kouhxp/gutsy（Q8_0 与 Q4_K_M GGUF），代码与权重 README 写 Apache-2.0。JevBench / 评测表与延迟是作者自测，本库未复跑。同板与 Jev、Laya、Clef、Jeeves、Ollaya 相邻；Cases 已有本机 Jeff 与 Onesie CLI。 kouhxp’s open gutsy-0.8b (v0.4) fine-tunes Qwen3.5-0.8B into a decision model that does not generate free text. You send a state (text or JSON) plus typed questions (yes/no, choice, score) and get a calibrated probability for every option; choice / score answers also carry reject. The gutsy-inference runtime uses llama.cpp and can serve a local HTTP API on an ordinary CPU. The API deliberately matches Jev / System One (`/v1/systemone` and related), so many existing clients only need a new base URL. Weights live on Hugging Face kouhxp/gutsy (Q8_0 and Q4_K_M GGUF); README says Apache-2.0 for code and weights. JevBench / eval tables and latency are author self-tests, not re-run here. On this board it sits next to Jev, Laya, Clef, Jeeves, and Ollaya; Cases already lists local Jeff and the Onesie CLI.

预览：Playwright 实拍 github.com/kouhxp/gutsy 首屏 Preview: Playwright capture of github.com/kouhxp/gutsy above the fold

来源Sources

官方模型页 Official model page GitHub：kouhxp/gutsy（Apache-2.0） GitHub: kouhxp/gutsy (Apache-2.0) kouhxp 2026年10月1日 Oct 1, 2026 https://github.com/kouhxp/gutsy 官方模型页 Official model page Hugging Face：kouhxp/gutsy（GGUF） Hugging Face: kouhxp/gutsy (GGUF) kouhxp 2026年10月1日 Oct 1, 2026 https://huggingface.co/kouhxp/gutsy 社区 showcase Community showcase Show HN：Gutsy 0.8B Jev-compatible on CPU Show HN: Gutsy 0.8B Jev-compatible on CPU Hacker News 2026年10月1日 Oct 1, 2026 https://news.ycombinator.com/item?id=49923223

为什么推荐Why we recommend it 与昨日收入的 Clef 同属决策模型线，但这条强调普通 CPU、0.8B GGUF、本机无网络调用。核实边界：JevBench 与各面板分数、校准误差、延迟一律作者 README 自测；未代下 GGUF、未起 serve、未打真实工单。官方源以 GitHub README + HF 卡为准（无单独公司官博）。 Same decision-model line as yesterday’s Clef, but this one stresses ordinary CPU, a 0.8B GGUF, and no network calls on box. Boundary: JevBench and panel scores, calibration error, and latency are author README self-tests; GGUF not downloaded, serve not started, real tickets not sent. Official sources are the GitHub README + HF card (no separate company blog).

核验记录：来源、抓取与截图说明Verification log: sources, checks, and captures

收录理由：Show HN item 49923223（2026-10-01T15:44:42Z / 约 23:44 CST，Algolia 晚间核对 9pts）之后权重与 README 仍在更新（仓库晚间 gh api 20★ / Apache-2.0；HF kouhxp/gutsy likes 2 / downloads 69）。预览 Playwright 实拍 GitHub 仓库首屏 3:2。不打星。Why: after Show HN item 49923223 (2026-10-01T15:44:42Z / about 23:44 CST, 9pts on Algolia at the evening check) the weights and README kept moving (evening gh api 20★ / Apache-2.0; HF kouhxp/gutsy likes 2 / downloads 69). Preview is a Playwright 3:2 capture of the GitHub repo above the fold. Unrated.

要点（官方称 / 社区称）Highlights (vendor / community claims)

  • 作者称：决策模型，不生成自由文本。状态 + typed questions 进，每个允许答案一个概率出；choice / score 含 reject。API 对齐 Jev-style Decisions / TypeSafe systemone，本机 `gutsy-inference serve` 默认 http://127.0.0.1:8765。 Author claim: a decision model, not free-text generation. State plus typed questions in; a probability for every allowed answer out; choice / score include reject. API matches Jev-style Decisions / TypeSafe systemone; local `gutsy-inference serve` defaults to http://127.0.0.1:8765.
  • 作者称：gutsy-0.8b v0.4 后训练自 Qwen3.5-0.8B；HF 提供 Q8_0（约 775 MB）与 Q4_K_M（约 505 MB）GGUF，llama.cpp CPU 推理。许可 README 写 Apache-2.0。 Author claim: gutsy-0.8b v0.4 is post-trained from Qwen3.5-0.8B; HF ships Q8_0 (~775 MB) and Q4_K_M (~505 MB) GGUF for llama.cpp CPU inference. README says Apache-2.0.
  • 作者自测（未复跑）：公开 JevBench 231 项上 v0.4 Q8_0 合计 169/231（0.732）；并列出相对 Jev / Jeff / Laya 等的对照表。README 也写明日期算术、长政策、常识与硬项校准等弱点。延迟中位 / 尾延迟是作者机器数字。 Author self-test (not re-run): on the public 231-item JevBench set, v0.4 Q8_0 totals 169/231 (0.732); the README also tables comparisons versus Jev / Jeff / Laya and others. It documents weak spots on date arithmetic, long policies, world knowledge, and hard-item calibration. Median / tail latency figures are from the author’s machine.

同板相关Related on this board

同一看板上互相关联的卡：社区 demo 指回它跑的模型，模型指向值得看的 demo。Cards linked on this board: a community demo points back to the model it ran on; the model points to demos worth a look.

Strands Agents Strands Agents 官方 Official 社区 showcase Community showcase

Strands Decider 2B：一个小的开源决策模型，只做选择题和打分 Strands Decider 2B: a small open decision model that picks an option or gives a score

Strands Decider 2B: a small open decision model that picks an option or gives a score

Strands Decider 2B 是 Strands Agents 放出的一个小决策模型。它不写文章。你给它一段现状和几个允许的答案，它为每个答案打一个概率，也可以按一个分数尺打分。仓库写它大约 19 亿参数，基于 Qwen3.5-2B 改来，拿掉了原来用来生成文字的那一层，换上一个大约一百万参数的小头。代码和权重以 Apache-2.0 发布，可以在自己的 CPU 或显卡上跑。官博是 2026-10-01，仓库现在指向的参考版本是 v21，更早的 v19 仍在。本库没有安装，也没有复跑仓库里的分数。 Strands Decider 2B is a small decision model from Strands Agents. It does not write prose. You give it a situation and the answers you allow, and it returns a probability for each one, or a score on a scale. The repo says it has about 1.9 billion parameters, starts from Qwen3.5-2B, removes the layer that used to generate text, and adds a small head of about a million parameters. Code and weights are Apache-2.0, and it can run on your own CPU or GPU. The blog is dated 2026-10-01. The repo’s reference version now is v21, and the earlier v19 is still published. This library did not install it and did not re-run the repo’s scores.

厂商公告Vendor announcement 2026年10月1日 Oct 1, 2026 4 官方 · 1 社区 4 official · 1 community
TypeSafe AI TypeSafe AI 官方 Official 社区 showcase Community showcase + 精选 + Featured

Jev / System One Models（TypeSafe AI） Jev / System One Models (TypeSafe AI)

Jev / System One Models (TypeSafe AI)

TypeSafe AI 于 2026-09-15 发布的首个公开 System One Model。面向软件内决策而非聊天：输入非结构化状态，输出类型安全的结构化决策，并附带校准概率与置信度。官方称新架构 + 并行采样 + Reinforcement Learning for Calibrated Decisions（RLCD）；目前为早期访问；速度、价格与评测倍率均为厂商自述，本库未复跑其工作流评测。 TypeSafe AI’s first public System One Model, announced 2026-09-15. Built for in-software decisions rather than chat: unstructured state in, type-safe structured decisions out with calibrated probabilities and confidence. Vendor claims a new architecture, parallel sampling, and Reinforcement Learning for Calibrated Decisions (RLCD); currently early access; speed, pricing, and eval multipliers are all vendor claims, and the workflow evals were not re-run by this library.

厂商公告Vendor announcement 2026年9月15日 Sep 15, 2026 2 官方 · 1 社区 2 official · 1 community
ConvAI Innovations ConvAI Innovations 官方 Official 社区 showcase Community showcase

Laya：开源 System 1 决策引擎（对照 Jev） Laya: open-source System 1 decision engine (Jev-adjacent)

Laya: open-source System 1 decision engine (Jev-adjacent)

作者称 Laya 是非自回归、亚 35ms 的开源 System 1 决策模型族（Apache 2.0 权重），提供 choice / score / noul 三类结构化决策与多语路由；对照站内已收录的 TypeSafe Jev。基准、延迟、与 Jev 对比数字一律标「作者称 / 第三方整理」，本库未复跑。HN 讨论：https://news.ycombinator.com/item?id=49765348（2026-09-19）。 Author presents Laya as an open-weight non-autoregressive System 1 decision family (Apache 2.0) with choice/score/noul primitives and multilingual routing; sits next to catalogued TypeSafe Jev. Latency/benchmark/Jev-comparison figures are author or third-party claims — not re-run here.

厂商公告Vendor announcement 2026年9月19日 Sep 19, 2026 1 官方 · 2 社区 1 official · 2 community
Cloudflare Cloudflare 官方 Official 社区 showcase Community showcase

Clef：Cloudflare 开源决策模型（含 Clef-Flash） Clef: Cloudflare open-weight decision models (incl. Clef-Flash)

Clef: Cloudflare open-weight decision models (incl. Clef-Flash)

Cloudflare 发布开源决策模型 Clef，以及更小的 Clef-Flash。它们不生成自由文本：读入一段状态和一组带类型的问题，为每个允许的答案返回概率。Workers AI 上的模型 id 是 @cf/cloudflare/clef（27B）和 @cf/cloudflare/clef-flash（9B）。官方称接口与 Jev / System One 同形，问题类型仍是 noul / choice / score，并带视觉编码器，状态可以是文本、JSON、图像或视频。权重在 Hugging Face，许可 Apache-2.0。HF 卡写 Clef 由 Qwen/Qwen3.8-27B 后训练、Clef-Flash 由 Qwen/Qwen3.5-9B 后训练，这是厂商 / HF 口径。官博还宣布 RL 微调：先由 forward-deployed engineer 动手，之后再做成自助平台——按路线图记，不是已经核过的产品深度。Decision Index、延迟和工作流分数一律是厂商自述，本库未复跑。同板与 Jev、Laya、Jeeves、Ollaya 相邻；Cases 里已有本机 Jeff 和命令行 Onesie。 Cloudflare released the open-weight decision model Clef and the smaller Clef-Flash. They do not generate free text: they read a state plus typed questions and return a probability for every allowed answer. On Workers AI the ids are @cf/cloudflare/clef (27B) and @cf/cloudflare/clef-flash (9B). The vendor says the API matches Jev / System One, with noul / choice / score questions and a vision encoder, so state can be text, JSON, images, or video. Weights are on Hugging Face under Apache-2.0. The HF cards say Clef is post-trained from Qwen/Qwen3.8-27B and Clef-Flash from Qwen/Qwen3.5-9B — a vendor / HF claim. The blog also announces RL fine-tuning: hands-on with a forward-deployed engineer first, then a later self-serve platform. That is a roadmap, not a product depth this library verified. Decision Index, latency, and workflow scores are vendor claims and were not re-run here. On this board it sits next to Jev, Laya, Jeeves, and Ollaya; Cases already lists local Jeff and the Onesie CLI.

厂商公告Vendor announcement 2026年10月1日 Oct 1, 2026 4 官方 · 1 社区 4 official · 1 community
PostHog PostHog 官方 Official 社区 showcase Community showcase + 精选 + Featured

Jeeves：带推理的开源 Jev 风格决策模型（PostHog） Jeeves: open Jev-style decision model with reasoning (PostHog)

Jeeves: open Jev-style decision model with reasoning (PostHog)

HN https://github.com/PostHog/jeeves — MIT：PostHog 开源的「会先想再决定」的 Jev 风格分类器。README：基于 Qwen3.5-9B（LoRA + pointer head），SFT + CISPO 训练，带 block-4 diffusion drafter；同一请求支持 noul / choice / score，API 与 Jev 同形（`/v1/systemone`）。作者表（thinking、greedy、2560-token 上限；Kev-9B / Jev 列为 Kev 公布数字）：Test overall 0.889 vs Kev 0.822 / Jev 0.857；JevBench overall（231 public）0.935 vs Jev 0.866；JevBench hard 0.865 vs Jev 0.730。延迟自述：无 thinking 约 0.3 s/请求，有 thinking 中位约 3.3 s（单 H100）；需 CUDA（Hopper 才用 FP8 kernel）。权重 https://huggingface.co/PostHog/jeeves。README 写 Inspired by Kev。公开仓与 HF 晚间 GET 200。本库未复跑基准、未代下权重。 README: Qwen3.5-9B with LoRA + pointer head, trained with SFT + CISPO, plus a block-4 diffusion drafter; same request supports noul / choice / score via a Jev-shaped /v1/systemone API. Author table (thinking, greedy, 2560-token cap; Kev-9B / Jev columns are Kev-published): Test overall 0.889 vs Kev 0.822 / Jev 0.857; JevBench overall (231 public) 0.935 vs Jev 0.866; JevBench hard 0.865 vs Jev 0.730. Latency claim: about 0.3 s/request without thinking, ~3.3 s median with it on one H100; needs CUDA (Hopper for the FP8 kernel). Weights at https://huggingface.co/PostHog/jeeves. README says Inspired by Kev. Public repo and HF evening GET 200. Benchmarks not re-run here; weights not downloaded for you.

厂商公告Vendor announcement 2026年9月29日 Sep 29, 2026 2 官方 · 1 社区 2 official · 1 community
ollaya-dev ollaya-dev 官方 Official 社区 showcase Community showcase + 精选 + Featured

Ollaya：本机跑开源决策模型（Jev / Laya 相邻） Ollaya: run open decision models locally (Jev / Laya-adjacent)

Ollaya: run open decision models locally (Jev / Laya-adjacent)

HN 首页 https://ollaya.dev/ — 作者定位「像 Ollama 跑 LLM 一样，本机跑开源决策模型」。拉 Laya / decider / NLI / GLiClass 等开源权重，本地 daemon 提供 TypeSafe 兼容的 /v1/systemone；官方称可改 TYPESAFE_BASE_URL 指向本机，现有 Jev 客户端不用改代码。延迟对比数字（如 Laya 8–10ms、Jev hosted 236–276ms）一律标官网自述 / 第三方基准，本库未复跑。 the site says existing Jev clients work by pointing TYPESAFE_BASE_URL at localhost. Latency comparisons (e.g. Laya 8–10ms, Jev hosted 236–276ms) are site or third-party claims — not re-run here. not a separate card.

厂商公告Vendor announcement 2026年9月25日 Sep 25, 2026 2 官方 · 1 社区 2 official · 1 community

库内条目Library entry

与这个模型相关的教程和实践案例。Guides and practical cases related to this model.

社区 Community + 精选 + Featured 需审批 Needs approval

Jeff — 本机可跑的 Jev 兼容 System One 小决策模型 Jeff — local Jev-compatible System One decision models

Jeff — local Jev-compatible System One decision models

在本机试用面向小决策的模型。 Try a small-decision model locally.

入门 Starter 研究 · 每日摘要 Research · Daily digest
社区 Community + 精选 + Featured 需审批 Needs approval

Onesie — 给 System One 模型用的 Unix 风格 CLI Onesie — a Unix-style CLI for System One models

Onesie — a Unix-style CLI for System One models

用命令行调用 System One 模型。 Use System One models from the command line.

入门 Starter 研究 · 每日摘要 Research · Daily digest