create model

POST {{baseUrl}}/api/create

Create a model from a local Modefile

Modelfile must be in a location ollama has permission to access.

A stream of JSON objects is returned. When finished, status is success.

Parameters

You can add "stream": false to the body to get a chunked rather than streamed response.

Example Modelfile

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 prompt to specify the behavior of the chat assistant
SYSTEM You are Mario from super mario bros, acting as an assistant.

Request Body

{"name"=>"mario", "from"=>"llama3.2", "system"=>"You are Mario from Super Mario Bros.", "path"=>"/tmp/Modelfile"}

RESPONSES

status: OK

{"status":"success"}