gmonair
/

Qwen2.5-Math-72B-Instruct-W4A16-padded

compressed-tensors

Model card Files Files and versions Community

Qwen2.5-Math-72B-Instruct-W4A16-padded / generation_config.json

gmonair's picture

Upload folder using huggingface_hub

8a0baf1 verified 2 days ago

history blame contribute delete

139 Bytes

	{
	"bos_token_id": 151643,
	"eos_token_id": [
	151645,
	151643
	],
	"pad_token_id": 151643,
	"transformers_version": "4.46.1"
	}