Curl call for testing LLM
PROMPT="What is the capital of France?" curl -s http://192.168.18.49:8080/v1/chat/completions -H "Content-Type: application/json" -d "$(jq -n --arg p "$PROMPT" '{"model":"GLM-Z1-Rumination-Q5-Chat","stream":false,"messages":[{"role":"system","content":"You are a helpful assistant. Always provide a final answer after your reasoning."},{"role":"user","content":$p}]}')"