微軟WizardLM-2模型忘了做測試,上線不到2天就撤下
· 2024-04-18

因為發布前忘了做測試,微軟臨時撤下原本在GitHub和Hugging Face公布的新一代大型語言模型WizardLM-2專案文件及程式碼檔案

微軟周三終於解釋原因,表示由於不太熟悉新的模型發布流程,在上線後發現他們忘了為WazardLM-2模型進行毒性測試(toxicity testing)。開發團隊目前正加緊完成測試,等完成後會儘速重新發布。

周一微軟公布WizardLM-2 LLM 7B、70B以及8x22B MoE三個版本。根據微軟稍早推文,微軟說明,相較Claude 3 Opus&Sonnet、GPT-4等LLM,WizardLM-2 8x22B是最先進的模型,根據內部以複雜任務的標竿測試,也是最佳開源LLM。WizardLM-2 70B具備最頂級推論能力,也是同等級模型(Mistral Medium&Large、Claude 2.1)中第一選擇。WizardLM-2 7B的效能也堪比規模大其10倍的開源模型。

AI模型競賽白熱化,Meta預告將在5月公布Llama 3首個版本,而OpenAI也預計今年夏天發表GPT-5。

Popular articles
Vietnam's tightening online gaming policy creates new market opportunities
Southeast Asia
Kazakhstan plans to penalise online casino promotions
Regulation
GAT Expo Puerto Rico Will Pulse with the New Era of Gaming in the Caribbean
Marketing
1spin4win grows its Latin American presence by partnering with Fortuna Juegos
Online Game
GGC Awards 2026 Shines in Colombo: Honoring Leaders and Innovators in the iGaming Industry
HUIDU Focus
British gambling levy rates confirmed for each vertical
Regulation
UK MPs reopen 2025 gambling inquiry as reform stalls
Regulation
Institutional Academy that exceeded expectations marked the opening of GAT CDMX
Online Game
Online gambling, crypto pose ongoing money laundering risks in Philippines, analyst says
Southeast Asia
New Jersey July Gambling Revenue Hits $606M, Sweeps Casinos Banned
Regulation
Are you ready to maximize your earnings? Try ProPush.me Constructor!
Marketing
1spin4win releases unique slot Don Catleone Hold and Win featuring gangster cats
Online Game
Super PAC Raises $48 Million: Sports Betting Forces Ramp Up Political Push
Regulation
Indiana online casino bill stalls in House committee
Regulation
Across 6 Cities: HUIDU Invites You to 8 World Cup Parties Redefining High-Value Social Networking
HUIDU Focus
Home
Game
Cooperation
Find
My