Edit model card

安装llama.cpp

保存gguf文件路径:../Mixtral-8x7B-instruction-zh_V0.1.Q4_K_S.gguf

linux系统下的测试:

进入安装的llama.cpp根目录下,

在命令行界面CLI下执行:

CUDA_VISIBLE_DEVICES=0 ./main -m ../Mixtral-8x7B-instruction-zh_V0.1.Q4_K_S.gguf -n 2048 -p "今年是2024年,大后年是哪年?"

Downloads last month
16
GGUF
Model size
46.7B params
Architecture
llama
Unable to determine this model’s pipeline type. Check the docs .