model-runner/cmd/cli/docs/reference/docker_model_package.yaml at 6a3fdac21313b6c9c1518b0c76706220931c2764 · docker/model-runner · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
command: docker model package
short: Package a model into a Docker Model OCI artifact
long: |-
    Package a model into a Docker Model OCI artifact.

    The model source must be one of:
      --gguf               A GGUF file (single file or first shard of a sharded model)
      --safetensors-dir    A directory containing .safetensors and configuration files
      --dduf               A .dduf (Diffusers Unified Format) archive
      --from               An existing packaged model reference

    By default, the packaged artifact is loaded into the local Model Runner content store.
    Use --push to publish the model to a registry instead.

    MODEL specifies the target model reference (for example: myorg/llama3:8b).
    When using --push, MODEL must be a registry-qualified reference.

    Packaging behavior:

      GGUF
        --gguf must point to a .gguf file.
        For sharded models, point to the first shard. All shards must:
          • reside in the same directory
          • follow an indexed naming convention (e.g. model-00001-of-00015.gguf)
        All shards are automatically discovered and packaged together.

      Safetensors
        --safetensors-dir must point to a directory containing .safetensors files
        and required configuration files (e.g. model config, tokenizer files).
        All files under the directory (including nested subdirectories) are
        automatically discovered. Each file is packaged as a separate OCI layer.

      DDUF
        --dduf must point to a .dduf archive file.

      Repackaging
        --from repackages an existing model. You may override selected properties
        such as --context-size to create a variant of the original model.

      Multimodal models
        Use --mmproj to include a multimodal projector file.
usage: docker model package (--gguf <path> | --safetensors-dir <path> | --dduf <path> | --from <model>) [--license <path>...] [--mmproj <path>] [--context-size <tokens>] [--push] MODEL
pname: docker model
plink: docker_model.yaml
options:
    - option: chat-template
      value_type: string
      description: absolute path to chat template file (must be Jinja format)
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
    - option: context-size
      value_type: uint64
      default_value: "0"
      description: context size in tokens
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
    - option: dduf
      value_type: string
      description: absolute path to DDUF archive file (Diffusers Unified Format)
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
    - option: format
      value_type: string
      default_value: docker
      description: |
        output artifact format: "docker" (default) or "cncf" (CNCF ModelPack spec)
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
    - option: from
      value_type: string
      description: reference to an existing model to repackage
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
    - option: gguf
      value_type: string
      description: absolute path to gguf file
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
    - option: license
      shorthand: l
      value_type: stringArray
      default_value: '[]'
      description: absolute path to a license file
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
    - option: mmproj
      value_type: string
      description: absolute path to multimodal projector file
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
    - option: push
      value_type: bool
      default_value: "false"
      description: |
        push to registry (if not set, the model is loaded into the Model Runner content store)
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
    - option: safetensors-dir
      value_type: string
      description: absolute path to directory containing safetensors files and config
      deprecated: false
      hidden: false
      experimental: false
      experimentalcli: false
      kubernetes: false
      swarm: false
deprecated: false
hidden: false
experimental: false
experimentalcli: false
kubernetes: false
swarm: false