Quantity vs quality in pottery is a lie16m ago Burnham claims EU summit could boost growth and help control illegal migration – UK politics live39m ago Base Models Can Detect Hidden Intentions that Prompted Classifiers Miss47m ago UK to strengthen cyber defences as minister calls for AI firms to increase safety efforts53m ago The Risks of Anthropomorphizing AI54m ago More research needed?56m ago Tesla's robotaxis face new regulator scrutiny over school zone-speeding claim57m ago I Asked Muse to Help Me Book My Holiday Travel. It Didn’t Fly Far.1h ago Can AI Keep Growing Exponentially? SemiAnalysis Makes the Case1h ago Microsoft Prepares to Put Gigawatts of Its Chips in Data Centers1h ago Is ‘Attention’ the Essence of Intelligence?2h ago What Alexandr Wang says he learned from Mark Zuckerberg's 'really long' WhatsApp DMs2h ago Google launches $180 Fitbit Edge with a bigger screen and AI coach2h ago Dystopian and dehumanising: that’s what it felt like when I was interviewed by an AI assistant2h ago

Quantity vs quality in pottery is a lie16m ago Burnham claims EU summit could boost growth and help control illegal migration – UK politics live39m ago Base Models Can Detect Hidden Intentions that Prompted Classifiers Miss47m ago UK to strengthen cyber defences as minister calls for AI firms to increase safety efforts53m ago The Risks of Anthropomorphizing AI54m ago More research needed?56m ago Tesla's robotaxis face new regulator scrutiny over school zone-speeding claim57m ago I Asked Muse to Help Me Book My Holiday Travel. It Didn’t Fly Far.1h ago Can AI Keep Growing Exponentially? SemiAnalysis Makes the Case1h ago Microsoft Prepares to Put Gigawatts of Its Chips in Data Centers1h ago Is ‘Attention’ the Essence of Intelligence?2h ago What Alexandr Wang says he learned from Mark Zuckerberg's 'really long' WhatsApp DMs2h ago Google launches $180 Fitbit Edge with a bigger screen and AI coach2h ago Dystopian and dehumanising: that’s what it felt like when I was interviewed by an AI assistant2h ago

Machine Learning Dev5 min reading time

JetBrains Releases Mellum2.1: A 12B MoE Open Model for Coding Agents

MarkTechPostPublished 4 days ago

Read the full article

JetBrains launched Mellum2.1, a 12-billion-parameter mixture-of-experts model optimized for coding agents, activating 2.5B parameters per token. It improves over Mellum2 mainly via reinforcement learning in real software environments, excelling in coding benchmarks and supporting long contexts.

#hugging-face #jetbrains #mellum2-1 #nvidia-h200 #reinforcement-learning #software-engineering

More in Machine Learning

Machine Learning3 min read

Microsoft launches a decision model built on Alibaba’s Qwen

The Next Web7h ago

Machine Learning

Nvidia Explores Deal Options With Reflection AI, Financial Times Says

Covered by 3 sources2d ago

Machine Learning15 min read

Import AI 476: Creativity and RSI; worse-than-China open weight models; AI goes to space

Import AI3h ago