# Copy to llamacpp-models.yaml (gitignored). Used when LLM_RUNTIME=llamacpp.
# url = direct HTTPS link to a .gguf; mmproj = vision projector (Qwen2.5-VL).
# Empty models: [] → only llama-server, GGUF клади вручную.
# Purpose: prompt-help / vision beside SwarmUI (RU/EN, low refusal).

models:
  # Recommended: Qwen2.5-VL 7B abliterate Q4_K_M + mmproj (~4.7 + 0.8 GB)
  - url: https://huggingface.co/mradermacher/Qwen2.5-VL-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-abliterated.Q4_K_M.gguf
    mmproj: https://huggingface.co/mradermacher/Qwen2.5-VL-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-abliterated.mmproj-Q8_0.gguf
    default: true

  # Text-only abliterate 7B (~4.7 GB):
  # - url: https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-7B-Instruct-abliterated-gguf/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q4_K_M.gguf

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