Arthur Mensch(@arthurmensch)
A new model to hasten AI progress. 24B, 81% MMLU, no RL for now! We're super excited to see the late...
6.0内容质量
TL;DR · AI 摘要
Arthur Mensch宣布了一个新的AI模型，该模型参数量为24B，MMLU得分为81%，目前没有使用RL。这个模型由Deepseek开发，他们对国际开源AI的发展感到兴奋。
核心要点
- 新AI模型参数量为24B
- MMLU得分81%
- 无RL训练
#AI#MMLU#Deepseek
打开原文Arthur Mensch on X: "A new model to hasten AI progress. 24B, 81% MMLU, no RL for now! We're super excited to see the latest development in international open-source AI (kudos to Deepseek!), and cannot wait to bring new contributions to it. We're renewing our commitment to using Apache licenses. AI" / X
Don’t miss what’s happening
A new model to hasten AI progress. 24B, 81% MMLU, no RL for now! We're super excited to see the latest development in international open-source AI (kudos to Deepseek!), and cannot wait to bring new contributions to it. We're renewing our commitment to using Apache licenses. AI
Quote
Mistral AI
@MistralAI
·
Jan 30, 2025
magnet:?xt=urn:btih:11f2d1ca613ccf5a5c60104db9f3babdfa2e6003&dn=Mistral-Small-3-Instruct&tr=udp%3A%2F%http://2Ftracker.opentrackr.org%3A1337%2Fannounce&tr=http%3A%2F%https://t.co/ua2yzvEYLu%3A1337%2Fannounce
105
163
1.5K
179
Read 105 replies