ewqr2130/

alignment-handbook-zephyr-7b_ppostep_100

alignment-handbook-zephyr-7b_ppo_step_100

2GPU, take the alignment-handbook-zephyr-7b-sft model, run the PPO on 100 steps.

=======================================================================

alignment-handbook-zephyr-7b_ppo_step_100

2GPU, take the alignment-handbook-zephyr-7b-sft model, run the PPO on 100 steps.

=======================================================================

alignment-handbook-zephyr-7b_ppo_step_100

2GPU, take the alignment-handbook-zephyr-7b-sft model, run the PPO on 100 steps.

=======================================================================