RichardErkhov/

ewqr2130_-_7B_ppo_phiRM_2GPU_3e-7step_4000-8bits

Quantization made by Richard Erkhov.

7B_ppo_phiRM_2GPU_3e-7step_4000 - bnb 8bits

zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B zephre 7B-sft---> PPO-7B