skymizer
/

Llama2-7b-sft-chat-custom-template-dpo

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Llama2-7b-sft-chat-custom-template-dpo / added_tokens.json

elichen3051's picture

Training in progress, step 43

1d3ee68 verified 8 months ago

history blame contribute delete

51 Bytes

	{
	"<\|im_end\|>": 32001,
	"<\|im_start\|>": 32000
	}