models.yaml

models:
  # Luna AI Llama 2 Uncensored
  - url: "https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGUF/resolve/main/luna-ai-llama2-uncensored.Q4_K_M.gguf"
    promptTemplate: |
      You are a helpful AI assistant.
      USER: {{.Input}}
      ASSISTANT:
    resources:
      requests:
        cpu: 8192m
        memory: 16384Mi
  # Mistral 7B Instruct 
  - url: "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf"
    promptTemplate: |
      <s>[INST] {{.Input}} [/INST] 
    resources:
      requests:
        cpu: 8192m
        memory: 16384Mi
  # GPT4All-J 6B
  - url: "https://gpt4all.io/models/ggml-gpt4all-j.bin"
    promptTemplate: |
      The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
      ### Prompt:
      {{.Input}}
      ### Response:
    resources:
      requests:
        cpu: 8192m
        memory: 16384Mi