Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
-
Updated
Aug 8, 2025 - Python
#
kimi-ai
Here are 5 public repositories matching this topic...
Educational implementation of Kimi-K2 architecture featuring Mixture of Experts, Muon optimizer & Latent Attention. The nanoGPT for next-gen transformers - simple, fast, and educational. Train/finetune Kimi-K2 models with ease!
-
Updated
Aug 5, 2025 - Python
Improve this page
Add a description, image, and links to the kimi-ai topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the kimi-ai topic, visit your repo's landing page and select "manage topics."