Files
home_stack/ai_stack/llamacpp.server/llama-server.service
T

31 lines
765 B
Desktop File

[Unit]
Description=Llama.cpp Server for Qwen3.5
After=network.target
[Service]
Type=simple
Environment="MODEL_PATH=%h/unsloth/Qwen3.5-0.8B-GGUF/Qwen3.5-0.8B-UD-Q4_K_XL.gguf"
Environment="MMPROJ_PATH=%h/unsloth/Qwen3.5-0.8B-GGUF/mmproj-BF16.gguf"
ExecStart=/usr/local/bin/llama-server \
--model ${MODEL_PATH} \
--mmproj ${MMPROJ_PATH} \
--temp 1.0 \
--top-p 0.95 \
--top-k 20 \
--min-p 0.00 \
--alias "unsloth/Qwen3.5-0.8B-GGUF" \
--cache-type-k q4_0 \
--cache-type-v q4_0 \
--host 0.0.0.0 \
--port 8011 \
--chat-template-kwargs '{"enable_thinking":false}'
Restart=always
RestartSec=5
User=%u
WorkingDirectory=%h/projects/home_stack/ai_stack/llamacpp.server
StandardOutput=journal
StandardError=journal
[Install]
WantedBy=multi-user.target