Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains
JetBrains has unveiled Mellum2, a new 12-billion-parameter Mixture-of-Experts (MoE) large language model. This model, a successor to Mellum, is designed to generate high-quality code and support various programming tasks.
JetBrains has officially introduced Mellum2, a powerful new large language model (LLM) built with a Mixture-of-Experts (MoE) architecture. Boasting 12 billion parameters, Mellum2 is a significant advancement over its predecessor, Mellum. The model is specifically designed for high-quality code generation and excels at a wide range of programming-related tasks.
Mellum2’s MoE architecture allows it to efficiently handle complex coding challenges. By leveraging specialized expert networks, the model can provide more accurate and contextually relevant suggestions for developers.
This release underscores JetBrains’ commitment to empowering developers with advanced AI tools. Mellum2 is expected to enhance productivity and streamline development workflows across various programming languages and environments.
Related articles
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
CUGA, IBM's open-source Agent Harness, simplifies building agentic applications by handling infrastructure, allowing developers to focus on tools and prompts. It offers pre-assembled components for planning, execution, and state management, significantly reducing development time. CUGA has topped agent benchmarks like AppWorld and WebArena.
OpenAI launches new initiative to help find and patch open source bugs
OpenAI has launched "Patch the Planet," a new initiative in partnership with cybersecurity firm Trail of Bits, to enhance the security of open-source projects. This program aims to assist maintainers in identifying and patching bugs, utilizing OpenAI's AI-powered security tools while reducing the burden on project teams.
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
Baidu has released PP-OCRv6, an advanced optical character recognition (OCR) model supporting 50 languages. Available on Hugging Face, this version significantly improves accuracy and efficiency across various parameter sizes, from 1.5 million to 34.5 million, marking a substantial leap in multilingual OCR technology.