@MiniMax_AI@melvynx I’m a massive advocate of minimax but there has been times - maybe 5-10 over the course of my billions of tokens that I’ve had stray Chinese characters. Not a real problem tho
Several sleepless nights later, M3 is finally here.
Coding frontier. 1M context. Native multimodal input.
The first open-weights model to bring all three together.
Hope you all like it 😎
p.s. M3 has already submitted a lot of PRs into MiniMax Code.