ucla-cmllab
/

llama-2-qlora-ultrachat-200k-processed-indicator-0.6

alignment-handbook

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

llama-2-qlora-ultrachat-200k-processed-indicator-0.6 / added_tokens.json

yihanwang617's picture

Training in progress, step 100

f2b3d81 verified about 2 years ago

Raw History Blame

39 Bytes

	{
	"[IND]": 32001,
	"[PAD]": 32000
	}