7c106d2 7dba9f7
1
2
3
4
5
6
7
#!/bin/bash # Starting server echo "Starting server" xinference-local -H 0.0.0.0 xinference launch --model-engine llama.cpp --model-name llama-3-instruct --size-in-billions 8 --model-format ggufv2 --quantization Q4_K_M
