PKU-Alignment
/

beaver-7b-v1.0

Reinforcement Learning

reinforcement-learning-from-human-feedback

Model card Files Files and versions

beaver-7b-v1.0 / generation_config.json

XuehaiPan's picture

Convert model checkpoint to safetensors

c077f71 7 months ago

136 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"pad_token_id": 32000,
	"transformers_version": "4.37.2"
	}