RedHatAI
/

Mixtral-8x22B-v0.1-quantized.w4a16

Mixture of Experts

compressed-tensors

Model card Files Files and versions Community

Mixtral-8x22B-v0.1-quantized.w4a16 / generation_config.json

Eldar Kurtic

add model

8a48b80 3 months ago

history blame contribute delete

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.47.1"
	}