There are many bugs when parsing the outpu of model. For example, which will make the reward model output the repeated result and don't return the score. In the condition, 'give up' doesn't work. I ...
The function EngineArgs.add_cli_args(parser) fails with TypeError: _StoreAction.__init__() got an unexpected keyword argument 'deprecated' in python 3.12 accroding to python docs the argument was ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback