amd
/

Mixtral-8x7B-Instruct-v0.1-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

Model card Files Files and versions

Mixtral-8x7B-Instruct-v0.1-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 / generation_config.json

XuebinWang's picture

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3)

d377d50 verified about 1 month ago

history blame contribute delete

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.55.1"
	}