Created
June 5, 2024 14:51
-
-
Save castrojo/15e58c0371d5fd7badf4a6cbf06e5c10 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
❯ cat .config/mods/mods.yml | |
# Default model (gpt-3.5-turbo, gpt-4, ggml-gpt4all-j...). | |
default-model: llama3 | |
# Text to append when using the -f flag. | |
format-text: Format the response as markdown without enclosing backticks. | |
# Ask for the response to be formatted as markdown unless otherwise set. | |
format: false | |
# Render output as raw text when connected to a TTY. | |
raw: false | |
# Quiet mode (hide the spinner while loading). | |
quiet: false | |
# Temperature (randomness) of results, from 0.0 to 2.0. | |
temp: 1.0 | |
# TopP, an alternative to temperature that narrows response, from 0.0 to 1.0. | |
topp: 1.0 | |
# Turn off the client-side limit on the size of the input into the model. | |
no-limit: false | |
# Include the prompt from the arguments in the response. | |
include-prompt-args: false | |
# Include the prompt from the arguments and stdin, truncate stdin to specified number of lines. | |
include-prompt: 0 | |
# Maximum number of times to retry API calls. | |
max-retries: 5 | |
# Your desired level of fanciness. | |
fanciness: 10 | |
# Text to show while generating. | |
status-text: Generating | |
# Default character limit on input to model. | |
max-input-chars: 12250 | |
# Maximum number of tokens in response. | |
# max-tokens: 100 | |
# Aliases and endpoints for OpenAI compatible REST API. | |
apis: | |
openai: | |
base-url: https://api.openai.com/v1 | |
api-key-env: OPENAI_API_KEY | |
models: | |
gpt-4: | |
aliases: ["4"] | |
max-input-chars: 24500 | |
fallback: gpt-3.5-turbo | |
gpt-4-32k: | |
aliases: ["32k"] | |
max-input-chars: 98000 | |
fallback: gpt-4 | |
gpt-3.5-turbo: | |
aliases: ["35t"] | |
max-input-chars: 12250 | |
fallback: gpt-3.5 | |
gpt-3.5-turbo-16k: | |
aliases: ["35t16k"] | |
max-input-chars: 44500 | |
fallback: gpt-3.5 | |
gpt-3.5: | |
aliases: ["35"] | |
max-input-chars: 12250 | |
fallback: | |
localai: | |
# LocalAI setup instructions: https://github.com/go-skynet/LocalAI#example-use-gpt4all-j-model | |
base-url: http://localhost:8080 | |
models: | |
ggml-gpt4all-j: | |
aliases: ["local", "4all"] | |
max-input-chars: 12250 | |
fallback: | |
azure: | |
# Set to 'azure-ad' to use Active Directory | |
# Azure OpenAI setup: https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource | |
base-url: https://YOUR_RESOURCE_NAME.openai.azure.com | |
api-key-env: AZURE_OPENAI_KEY | |
models: | |
gpt-4: | |
aliases: ["az4"] | |
max-input-chars: 24500 | |
fallback: gpt-35-turbo | |
gpt-35-turbo: | |
aliases: ["az35t"] | |
max-input-chars: 12250 | |
fallback: gpt-35 | |
gpt-35: | |
aliases: ["az35"] | |
max-input-chars: 12250 | |
fallback: | |
ollama: | |
base-url: http://localhost:11434/api | |
models: | |
"llama3:latest": | |
aliases: ["llama3"] | |
max-input-chars: 650000 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment