Quantization made by Richard Erkhov.
alignment-handbook-zephyr-7b_ppo_5e7step_51 - bnb 4bits
Original model description:
license: apache-2.0
ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51
runing the SFT with PPO for 51 steps.
runing the SFT with PPO for 51 steps.
runing the SFT with PPO for 51 steps.
runing the SFT with PPO for 51 steps.
runing the SFT with PPO for 51 steps.
