WGNW
/

llama-2-7b-ko-auto-gptq-full-v2

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

llama-2-7b-ko-auto-gptq-full-v2 / special_tokens_map.json

WGNW's picture

AutoGPTQ model for llama-2-7b-ko-full: 4 bits

578d554 about 1 year ago

72 Bytes

	{
	"bos_token": "<s>",
	"eos_token": "</s>",
	"unk_token": "<unk>"
	}