Update MiniMax model ID from m2.1 to m2.5

2026-03-06 16:47:48 +08:00
parent 014a5b712d
commit 32636ecf8a
3 changed files with 4 additions and 4 deletions
--- a/website/docs/user-guide/features/rl-training.md
+++ b/website/docs/user-guide/features/rl-training.md
@@ -147,7 +147,7 @@ Default configuration:
 - Tests 3 models at different scales for robustness:
  - `qwen/qwen3-8b` (small)
  - `z-ai/glm-4.7-flash` (medium)
-  - `minimax/minimax-m2.1` (large)
+  - `minimax/minimax-m2.5` (large)
 - Total: ~144 rollouts

 This validates: