PrunaAI
/

NousResearch-Nous-Hermes-Llama2-13b-QUANTO-int4bit-smashed

Inference Endpoints

Model card Files Files and versions Community

NousResearch-Nous-Hermes-Llama2-13b-QUANTO-int4bit-smashed / added_tokens.json

sharpenb's picture

0ad18f56ae9e0efd7cfe27413b08cdd48ffda99b6f0a9d16224b04ca08f6ca3c

b55c74a verified 5 months ago

21 Bytes

	{
	"<pad>": 32000
	}