跳到正文
𝕏 ModelScope(x.com)·· 17 天前精選品質評分68
重點導讀

EMLab KnowLine 推出七款開放權重決策模型,涵蓋供 RAG、AI 助理框架與企業工作流程使用的稠密模型及 MoE 選項。

  • 模型與評測:稠密模型規模從 0.8B 到 31B,另有兩款 MoE。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

推薦理由

七款模型涵蓋不同規模與稀疏啟用配置,並提供私有測試分數、延遲及機率校準資料,可比較其決策能力與部署取捨。

ModelScope
ModelScope@ModelScope2022
·17 天前
𝕏

EMLab's KnowLine offers seven open-weight decision models for RAG, agent harnesses, and enterprise workflows, spanning dense models from 0.8B to 31B plus two MoE options. 🤖https://t.co/0GmwVR9MAl

🏆 SOTA on private decision tests: KnowLine-31B-Gen1 achieves 71.86 on Jev Decision Index 0.4.1 Full. The score combines private same-skill and new-domain tests, excluding public-suite results.

⚡ Low latency with sparse activation: KnowLine-35B-A3B-Gen1.5 activates about 3B parameters and scores 65.77 Full, with 47.1 ms median latency on the leaderboard's single RTX PRO 6000 setup.

✅ Measured probability calibration: In the 31B model's public-suite evaluation, approximately 0.9–1.0% of decisions made with at least 95% confidence were wrong. Validate thresholds on your own data.

🎯 Decisions throughout the workflow: Filter retrieved documents, check supporting evidence, select tools, route tickets, and score outputs through a Jev-compatible API supporting up to 64 questions per request.

🛠️ Adapt to your business: Continue post-training with ms-swift. The development loop uses research agents to construct and decontaminate data, train, evaluate, and retain or roll back changes based on evidence.

📜 Weights: Apache 2.0. Serving code: MIT.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論