wttw
/

Llama3-8B-CPP

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Llama3-8B-CPP / generation_config.json

wttw's picture

Upload LlamaForCausalLM

8924d12 verified 7 months ago

143 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": [
	128001,
	128009
	],
	"transformers_version": "4.40.1"
	}