跳到主内容
@wquguru
精选88Ollama(GitHub Releases)AI 编程与模型

Ollama v0.35.0-rc1:弃用 typical_p,新增 System One 评分 API

v0.35.0

原文
发到 X
推荐理由

typical_p 参数被正式弃用,直接破坏现有推理调用链路。依赖 Ollama API 的开发者或自动化脚本必须立即检查代码,确认是否使用了该参数并及时替换,以免后续版本彻底移除后导致服务异常。

What's Changed

更新内容

  • app: sync macOS update menu and icon at startup by @hoyyeva in #18622
  • app: defer Settings model discovery by @ParthSareen in #18598
  • app: isolate cloud-setting tests from Windows user config by @drifkin in #18626
  • api: deprecate typical_p by @dhiltgen in #18627
  • bench: use HumanEval patch prompts by @dhiltgen in #17480
  • feat: add System One scoring API by @ParthSareen in #18606
  • mlx: bound pull stall retries and let the watchdog interrupt them by @dhiltgen in #18625
  • app: 在启动时同步 macOS 更新菜单和图标 by @hoyyeva in #18622
  • app: 延迟设置模型发现 by @ParthSareen in #18598
  • app: 将云设置测试与 Windows 用户配置隔离 by @drifkin in #18626
  • api: 弃用 typical_p by @dhiltgen in #18627
  • bench: 使用 HumanEval patch prompts by @dhiltgen in #17480
  • feat: 添加 System One 评分 API by @ParthSareen in #18606
  • mlx: 限制 pull 停滞重试次数并让看门狗中断它们 by @dhiltgen in #18625

Full Changelog: v0.34.4...v0.35.0-rc1

完整更新日志: v0.34.4...v0.35.0-rc1

更进一步:量化金融体系

看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力

进入量化体系 →

相似阅读

关联信息,但可能不是同一事件