# Copy to llamacpp-models.yaml (gitignored). Used when LLM_RUNTIME=llamacpp.
# url = direct HTTPS link to a .gguf (Hugging Face resolve/main/…).
# Empty models: [] → only llama-server, GGUF клади вручную на VM.
# Purpose: prompt-help beside SwarmUI (RU/EN).

models:
  # Recommended: Qwen2.5 7B abliterate Q4_K_M (~4.7 GB)
  - url: https://huggingface.co/bartowski/huihui-ai_Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/huihui-ai_Qwen2.5-7B-Instruct-abliterated-Q4_K_M.gguf
    default: true

  # Lighter (~2 GB):
  # - url: https://huggingface.co/bartowski/Qwen2.5-3B-Instruct-GGUF/resolve/main/Qwen2.5-3B-Instruct-Q4_K_M.gguf

  # Official stock 7B (more refusals):
  # - url: https://huggingface.co/bartowski/Qwen2.5-7B-Instruct-GGUF/resolve/main/Qwen2.5-7B-Instruct-Q4_K_M.gguf