HF RL Explorer

Regression in 0.740 for init subclass

Regression in 0.740 for init subclass: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). Regression in 0.740 for initsubclass The following code does not throw errors in 0.730, but does in 0.740. Likely to do with 7723 And slightly more complicated, a self registering subclass:

The task

Regression in 0.740 for initsubclass The following code does not throw errors in 0.730, but does in 0.740. Likely to do with #7723 And slightly more complicated, a self registering subclass:

Part of XiaomiMiMo/MiMo-V2.6-RL-oss.