sfulay
/

zephyr-7b-dpo-full-gpt_consistent-reward-scale-1-rpo

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-gpt_consistent-reward-scale-1-rpo / generation_config.json

sfulay's picture

Model save

44bba64 verified 2 months ago

116 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.44.0.dev0"
	}