nm-testing
/

Pixtral-Large-Instruct-2411-hf-quantized.w8a8

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Pixtral-Large-Instruct-2411-hf-quantized.w8a8 / generation_config.json

Shubhra Pandit

Upload model files

c94e540 12 days ago

history blame contribute delete

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.48.2"
	}