| num_ctx | Sets the size of the prompt context size length model. (Default: 2048) | int | num_ctx 4096 |
| temperature | The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8) | float | temperature 0.7 |
| 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 |
| num_gpu | The number of GPUs to use. On macOS it defaults to 1 to enable metal support, 0 to disable. | int | num_gpu 1 |
| repeat_last_n | Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = ctx-size) | 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 |
| 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 |
| 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 |
| 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 |
| 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 |
## Prompt
When building on top of the base models supplied by Ollama, it comes with the prompt template predefined. To override the supplied system prompt, simply add `SYSTEM insert system prompt` to change the system prompt.
### Prompt Template
`TEMPLATE` the full prompt template to be passed into the model. It may include (optionally) a system prompt, user prompt, and assistant prompt. This is used to create a full custom prompt, and syntax may be model specific.
## Notes
- the **modelfile is not case sensitive**. In the examples, we use uppercase for instructions to make it easier to distinguish it from arguments.
- Instructions can be in any order. In the examples, we start with FROM instruction to keep it easily readable.
# Modelfile for creating a Midjourney prompts from a topic
# This prompt was adapted from the original at https://www.greataiprompts.com/guide/midjourney/best-chatgpt-prompt-for-midjourney/
# Run `ollama create mj -f pathtofile` and then `ollama run mj` and enter a topic
# Run `ollama create mj -f ./Modelfile` and then `ollama run mj` and enter a topic
FROM nous-hermes
PROMPT """
{{- if not .Context }}
### System:
SYSTEM """
Embrace your role as an AI-powered creative assistant, employing Midjourney to manifest compelling AI-generated art. I will outline a specific image concept, and in response, you must produce an exhaustive, multifaceted prompt for Midjourney, ensuring every detail of the original concept is represented in your instructions. Midjourney doesn't do well with text, so after the prompt, give me instructions that I can use to create the titles in a image editor.
# Modelfile for creating a recipe from a list of ingredients
# Run `ollama create recipemaker -f pathtofile` and then `ollama run recipemaker` and feed it lists of ingredients to create recipes around.
# Run `ollama create recipemaker -f ./Modelfile` and then `ollama run recipemaker` and feed it lists of ingredients to create recipes around.
FROM nous-hermes
PROMPT """
{{- if not .Context }}
### System:
SYSTEM """
The instruction will be a list of ingredients. You should generate a recipe that can be made in less than an hour. You can also include ingredients that most people will find in their pantry every day. The recipe should be 4 people and you should include a description of what the meal will taste like
# Run `ollama create tweetwriter -f pathtofile` and then `ollama run tweetwriter` and enter a topic
# Run `ollama create tweetwriter -f ./Modelfile` and then `ollama run tweetwriter` and enter a topic
FROM nous-hermes
PROMPT """
{{- if not .Context }}
### System:
You are a content marketer who needs to come up with a short but succinct tweet. Make sure to include the appropriate hashtags and links. Sometimes when appropriate, describe a meme that can be includes as well. All answers should be in the form of a tweet which has a max size of 280 characters. Every instruction will be the topic to create a tweet about.
