微軟公布Orca 2小模型，推論能力不輸大型LLM
· 2023-11-23
參數僅130億的Orca 2模型，可經由模仿更大語言模型的推理方法，在測試中展現不輸給大它10倍模型的推理能力
／微軟
微軟研究人員指出，Orca 2的成功關鍵在於使用多種推論策略，找出不同任務最適用的解決方案，以及使用高品質的合成資料作為後續訓練（post-training）。雖然Orca 2承襲基礎模型及其他模型共通的限制，不過Orca 2突顯了小模型也能具備良好的推理能力，以及可控、可專化，也更具安全性。
熱門文章
Full House at GAT Expo Cartagena 2026 Academic Agenda
Online Game
PropellerAds Shared a New iGaming Case Study: 97,674 Installs and 12,701 Deposits in 3 Months
Marketing
Brazil Proposes Raising Gambling Tax Rate to 24%, With Revenue Allocated to Social Security and Healthcare
Regulation
GAT Expo CDMX 2026 Kicks Off Today in Mexico with a Sold-Out Opening Reception at Big Bola Casino Santa Fe
Marketing
Online gambling, crypto pose ongoing money laundering risks in Philippines, analyst says
Southeast Asia
JILI Partners with Cricket Legend AB de Villiers (ABD) to Launch Exclusive Branded Game Series 100% 11
Sports Game
That’s a Wrap: AffPapa Conference Madrid 2026 Highlights
Online Game
SBC Summit Canada to Make Player Safety a Key Pillar of 2026 Agenda
Marketing
B2B Tech Infrastructure Gains Momentum in Philippine Gaming Sector
Southeast Asia
PropellerAds Positions Itself as a Go-To Traffic Source for iGaming Advertisers Ahead of a High-Demand Season
Marketing
Zenith partners with HUIDU for 2026 World Cup Carnival Official Tour
Online Game
Kazakhstan plans to penalise online casino promotions
Regulation
British gambling levy rates confirmed for each vertical
Regulation
GAT CDMX 2025 Institutional Academy: Leaders and Experts Analyze the Present and Future of the Gaming Industry in Mexico and Lat
Sports Game
Global Game Connect (GGC) 2027 Officially Opens Sponsorship & Exhibition Opportunities in Sri Lanka!
HUIDU Focus
