note

[Mellum 2.1] The shock of JetBrains' new open LLM: 12B parameters, 2.5B active, 47% on SWE-bench, and free for commercial use

It's a model that's a bit of a missed opportunity in some ways. Since it's 12B-2.5B, I was hoping I could use it with about ...

[Mellum 2.1]JetBrains의 신작 오픈 LLM이 12B, 액티브 2.5B로 SWE-bench 47% 달성 및 상업적 무료라는 충격

여러모로 아쉬운 점이 있는 모델이에요.12B-2.5B라서 VRAM 6GB 정도로 쓸 수 있지 않을까 싶었는데, 4bit 양자화로 8GB 정도는 필요하네요. 으음, 조금만 더 낮았으면 좋았을 텐데.JetBrains는 Kiro ...
blog.jetbrains.com

Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents

Trained with reinforcement learning in real environments, Mellum2.1 is built for coding agents and fast sub-agents that run ...
Homeland Security

Section 508 Training

The Department of Homeland Security (DHS) offers free online training to help you create and test digital content that is accessible to everyone. These courses teach you how to design and produce ...