sosuke
/

ELYZA-japanese-Llama-2-7b-8bit

Text Generation

Inference Endpoints

text-generation-inference

8-bit precision

Model card Files Files and versions Community

ELYZA-japanese-Llama-2-7b-8bit / generation_config.json

sosuke's picture

Upload LlamaForCausalLM

30eee06 7 months ago

raw history blame contribute delete

No virus

154 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"pad_token_id": 0,
	"transformers_version": "4.32.0",
	"use_cache": false
	}