amd-quark
/

llama-tiny-fp8-quant-method

Model card Files Files and versions Community

llama-tiny-fp8-quant-method / generation_config.json

fxmarty's picture

Upload folder using huggingface_hub

f21915c verified about 2 months ago

132 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 0,
	"eos_token_id": 1,
	"pad_token_id": 1,
	"transformers_version": "4.48.1"
	}