llmixer
/

Meta-Llama-3-70B-Instruct-8.0bpw-h8-exl2

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

Meta-Llama-3-70B-Instruct-8.0bpw-h8-exl2 / generation_config.json

llmixer's picture

Model upload

7ceba9c verified 7 months ago

126 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": 128001,
	"transformers_version": "4.40.0.dev0"
	}