neuralmagic-ent
/

Llama-3.1-70B-quantized.w8a8

compressed-tensors

Model card Files Files and versions Community

Llama-3.1-70B-quantized.w8a8 / generation_config.json

nm-research's picture

Upload folder using huggingface_hub

91fecb4 verified 18 days ago

history blame contribute delete

121 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": 128001,
	"transformers_version": "4.43.3"
	}