RedHatAI
/

Apertus-70B-Instruct-2509-quantized.w4a16

Text Generation

compressed-tensors

Model card Files Files and versions

Apertus-70B-Instruct-2509-quantized.w4a16 / generation_config.json

alexmarques's picture

Upload folder using huggingface_hub

eead3b9 verified 2 months ago

history blame contribute delete

137 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": [
	2,
	68,
	72
	],
	"transformers_version": "4.56.1"
	}