aio/cpu/vision.yaml

context_size: 4096
f16: true
backend: llama-cpp
mmap: true
mmproj: minicpm-v-4_5-mmproj-f16.gguf
name: gpt-4o
parameters:
  model: minicpm-v-4_5-Q4_K_M.gguf
stopwords:
- <|im_end|>
- <dummy32000>
- </s>
- <|endoftext|>
template:
  chat: |
    {{.Input -}}
    <|im_start|>assistant
  chat_message: |
    <|im_start|>{{ .RoleName }}
    {{ if .FunctionCall -}}
    Function call:
    {{ else if eq .RoleName "tool" -}}
    Function response:
    {{ end -}}
    {{ if .Content -}}
    {{.Content }}
    {{ end -}}
    {{ if .FunctionCall -}}
    {{toJson .FunctionCall}}
    {{ end -}}<|im_end|>
  completion: |
    {{.Input}}
  function: |
    <|im_start|>system
    You are a function calling AI model. You are provided with functions to execute. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
    {{range .Functions}}
    {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
    {{end}}
    For each function call return a json object with function name and arguments
    <|im_end|>
    {{.Input -}}
    <|im_start|>assistant

download_files:
- filename: minicpm-v-4_5-Q4_K_M.gguf
  sha256: c1c3c33100b15b4caf7319acce4e23c0eb0ce1cbd12f70e8d24f05aa67b7512f
  uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/ggml-model-Q4_K_M.gguf
- filename: minicpm-v-4_5-mmproj-f16.gguf
  uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/mmproj-model-f16.gguf
  sha256: 7a7225a32e8d453aaa3d22d8c579b5bf833c253f784cdb05c99c9a76fd616df8