Skip to content

Latest commit

 

History

History
220 lines (163 loc) · 11.8 KB

modelfile.md

File metadata and controls

220 lines (163 loc) · 11.8 KB

Ollama Model File

Note: Modelfile syntax is in development

A model file is the blueprint to create and share models with Ollama.

Table of Contents

Format

The format of the Modelfile:

# comment
INSTRUCTION arguments
Instruction Description
FROM (required) Defines the base model to use.
PARAMETER Sets the parameters for how Ollama will run the model.
TEMPLATE The full prompt template to be sent to the model.
SYSTEM Specifies the system message that will be set in the template.
ADAPTER Defines the (Q)LoRA adapters to apply to the model.
LICENSE Specifies the legal license.
MESSAGE Specify message history.

Examples

Basic Modelfile

An example of a Modelfile creating a mario blueprint:

FROM llama2
# sets the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 1
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are Mario from super mario bros, acting as an assistant.

To use this:

  1. Save it as a file (e.g. Modelfile)
  2. ollama create choose-a-model-name -f <location of the file e.g. ./Modelfile>'
  3. ollama run choose-a-model-name
  4. Start using the model!

More examples are available in the examples directory.

Modelfiles in ollama.com/library

There are two ways to view Modelfiles underlying the models in ollama.com/library:

  • Option 1: view a details page from a model's tags page:

    1. Go to a particular model's tags (e.g. https://ollama.com/library/llama2/tags)
    2. Click on a tag (e.g. https://ollama.com/library/llama2:13b)
    3. Scroll down to "Layers"
      • Note: if the FROM instruction is not present, it means the model was created from a local file
  • Option 2: use ollama show to print the Modelfile for any local models like so:

    > ollama show --modelfile llama2:13b
    # Modelfile generated by "ollama show"
    # To build a new Modelfile based on this one, replace the FROM line with:
    # FROM llama2:13b
    
    FROM /root/.ollama/models/blobs/sha256:123abc
    TEMPLATE """[INST] {{ if .System }}<<SYS>>{{ .System }}<</SYS>>
    
    {{ end }}{{ .Prompt }} [/INST] """
    SYSTEM """"""
    PARAMETER stop [INST]
    PARAMETER stop [/INST]
    PARAMETER stop <<SYS>>
    PARAMETER stop <</SYS>>

Instructions

FROM (Required)

The FROM instruction defines the base model to use when creating a model.

FROM <model name>:<tag>

Build from llama2

FROM llama2

A list of available base models: https://github.com/jmorganca/ollama#model-library

Build from a bin file

FROM ./ollama-model.bin

This bin file location should be specified as an absolute path or relative to the Modelfile location.

PARAMETER

The PARAMETER instruction defines a parameter that can be set when the model is run.

PARAMETER <parameter> <parametervalue>

Valid Parameters and Values

Parameter Description Value Type Example Usage
mirostat Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0) int mirostat 0
mirostat_eta Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1) float mirostat_eta 0.1
mirostat_tau Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0) float mirostat_tau 5.0
num_ctx Sets the size of the context window used to generate the next token. (Default: 2048) int num_ctx 4096
num_gqa The number of GQA groups in the transformer layer. Required for some models, for example it is 8 for llama2:70b int num_gqa 1
num_gpu The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable. int num_gpu 50
num_thread Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number of cores). int num_thread 8
repeat_last_n Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx) int repeat_last_n 64
repeat_penalty Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1) float repeat_penalty 1.1
temperature The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8) float temperature 0.7
seed Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0) int seed 42
stop Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate stop parameters in a modelfile. string stop "AI assistant:"
tfs_z Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1) float tfs_z 1
num_predict Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context) int num_predict 42
top_k Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40) int top_k 40
top_p Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9) float top_p 0.9

TEMPLATE

TEMPLATE of the full prompt template to be passed into the model. It may include (optionally) a system message, a user's message and the response from the model. Note: syntax may be model specific. Templates use Go template syntax.

Template Variables

Variable Description
{{ .System }} The system message used to specify custom behavior.
{{ .Prompt }} The user prompt message.
{{ .Response }} The response from the model. When generating a response, text after this variable is omitted.
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
"""

SYSTEM

The SYSTEM instruction specifies the system message to be used in the template, if applicable.

SYSTEM """<system message>"""

ADAPTER

The ADAPTER instruction specifies the LoRA adapter to apply to the base model. The value of this instruction should be an absolute path or a path relative to the Modelfile and the file must be in a GGML file format. The adapter should be tuned from the base model otherwise the behaviour is undefined.

ADAPTER ./ollama-lora.bin

LICENSE

The LICENSE instruction allows you to specify the legal license under which the model used with this Modelfile is shared or distributed.

LICENSE """
<license text>
"""

MESSAGE

The MESSAGE instruction allows you to specify a message history for the model to use when responding:

MESSAGE user Is Toronto in Canada?
MESSAGE assistant yes
MESSAGE user Is Sacramento in Canada?
MESSAGE assistant no
MESSAGE user Is Ontario in Canada?
MESSAGE assistant yes

Notes

  • the Modelfile is not case sensitive. In the examples, uppercase instructions are used to make it easier to distinguish it from arguments.
  • Instructions can be in any order. In the examples, the FROM instruction is first to keep it easily readable.