跳到正文
𝕏 ModelScope(x.com)·· 17 天前品質評分61
重點導讀

THX-02 是一款開源的 4.5B 多模態決策模型,可針對使用者提供的選項回傳機率,並在需要時加入選擇性推理。

  • 選擇性推理:自動模式會在直接答案不確定且內部閘控判定需要推理時,產生簡短推理說明,再結合直接預測與推理輔助預測。

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:

ModelScope
ModelScope@ModelScope2022
·17 天前
𝕏

THX-02 from @halx_ai is open source: a 4.5B multimodal decision model trained on requests up to 32K tokens, with a 60M adapter for selective thinking. It returns probabilities over your supplied options.
🤖 https://t.co/tkOTcHR0ov

🧠 Reason selectively: Auto mode generates a short reasoning note when the direct answer is uncertain and an internal gate identifies a need for reasoning, then combines the direct and thought-assisted predictions.

⚡ Fast direct decisions: Median latency is 50 ms directly and 79 ms in auto mode on one RTX PRO 6000. Requests that trigger thinking typically take 0.3–1 second.

📊 Measured gains from thinking: Auto mode raises Decision Index 0.3 from 63.83 to 65.06 on a 6,018-request public-suite sample. Full-suite and private leaderboard evaluations remain pending.

🎯 Define your own decisions: Ask up to 64 questions per request using multiple-choice, yes/no, or ordered ratings. New labels need no retraining.

🖼️ Text, images, and charts: Accepts up to four images per request, with post-training and evaluation across more than 20 languages.

📜 Apache 2.0.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論