Chat with llama.cpp

./build/bin/llama-server -hf Qwen/Qwen2-0.5B-Instruct-GGUF:Q2_K

curl -X POST http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "messages": [
            {"role": "user", "content": "Hello! How are you today?"}
        ],
        "max_tokens": 150,
        "temperature": 0.7
    }'

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm good, thanks! How can I assist you today?"
      }
    }
  ],
  "created": 1751341871,
  "model": "gpt-3.5-turbo",
  "system_fingerprint": "b5787-0a5a3b5c",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 14,
    "prompt_tokens": 15,
    "total_tokens": 29
  },
  "id": "chatcmpl-bGxdAhvPfBtQ8O5Uc9hrPGWFdv1w1m9e",
  "timings": {
    "prompt_n": 12,
    "prompt_ms": 96.768,
    "prompt_per_token_ms": 8.064,
    "prompt_per_second": 124.0079365079365,
    "predicted_n": 14,
    "predicted_ms": 216.101,
    "predicted_per_token_ms": 15.435785714285714,
    "predicted_per_second": 64.78452205218855
  }
}