- bestLlama: 'true'
  description: The official open assistant 30B model finally here
  filename: OpenAssistant-SFT-7-Llama-30B.ggml.q4_0.bin
  license: Non commercial
  owner_link: https://huggingface.co/TheBloke
  owner: TheBloke
  server: https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-GGML/resolve/main/
  sha256: 32fd44c685fbf429810db593e2db8aa42a7e1be2cd3571b6005d53b029acfcf5
- bestLlama: 'true'
  description: Legacy version of Vicuna 7B v 1.1 Quantized on 4 bits
  filename: legacy-ggml-vicuna-7B-1.1-q4_0.bin
  license: Non commercial
  owner_link: https://huggingface.co/CRD716
  owner: CRD716
  server: https://huggingface.co/CRD716/ggml-vicuna-1.1-quantized/resolve/main/
  sha256: 67efec973a81151a55e55f8e747b455354979492978b2f9f22a342c6d841e6b7