Ollama Releases New Updates
Decision models can now be run directly from the terminal with 'ollama run' commands, and more.
What happened
According to Ollama (GitHub releases), the latest update includes several key features, including the ability to run decision models directly from the terminal with 'ollama run' commands.
Why it matters
This enhancement enables users to work more efficiently with decision models, making it easier to integrate them into their workflows.
Key details
The 'ollama run' command allows users to run decision models without leaving the terminal, while the 'ollama launch' command enables the use of usage credits without requiring a paid plan. Additionally, the 'ollama launch codex' command now includes locally installed models in its model picker, allowing for easy swapping.
Sources
Related stories
Ollama Updates MLX Runtime and Supports New Models
Ollama's MLX runtime now runs model architectures on Apple Silicon devices by default, and the platform has added support for several new models.
Mistral's Le Chonk Model Challenges Top AI Models
Mistral releases a new AI model, Le Chonk, with 1 trillion parameters, optimized for various domains, and available for customization.
Telecom Operators Shift to Open Models for AI
NVIDIA's report reveals a significant 89% shift towards open models among telecom operators, enabling trust, control, and customization of AI capabilities.
OpenAI Releases Mathematical Breakthroughs
The AI research organization publishes a batch of 722 mathematical manuscripts, covering 372 result families and solving hundreds of open questions.
GitHub Introduces Evergreen for Secure Access and Repository Hygiene
GitHub's Evergreen workflow automates organization hygiene and secure access reviews.
edithero benchmark for long-horizon 3d editing
The EditHero benchmark is introduced to evaluate and improve the reliability of long-horizon, part-level 3D editing.