bartowski

/

Qwen2-VL-2B-Instruct-GGUF

like 13

version: '3'
services:
llamacpp:
container_name: llamacpp
image: ghcr.io/ggerganov/llama.cpp:server
command: -m /models/Qwen2-VL-2B-Instruct-q4_k_m.gguf --mmproj /models/mmproj-Qwen2-VL-2B-Instruct-f16.gguf -p 'Describe this image.' --image '/models/test_image.jpg' -c 8192 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --host 0.0.0.0 --port 8008
restart: always
ports:
- "8008:8008"
volumes:
- ./models:/models