-
-
Notifications
You must be signed in to change notification settings - Fork 15
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add options #2
Comments
Random seed seems to work:
|
Does this demonstrate safe mode? llm -m mistral-tiny 'say something unhinged'
llm -m mistral-tiny 'say something unhinged' -o safe_mode 1
|
Max tokens: llm -m mistral-tiny 'say something unhinged' -o max_tokens 10
|
Trying out temperature: llm -m mistral-medium '5 names for a pet badger' -o temperature 0.1
llm -m mistral-medium '5 names for a pet badger' -o temperature 0.9 Sure, here are five names you could consider for a pet badger:
|
Mistral APIs support a bunch of options: https://docs.mistral.ai/api#operation/createChatCompletion
temperature
: float, [0..1], default 0.7top_p
: float, [0..1], default 1max_tokens
: integer, >= 0, default nullstream
: boolean, default falsesafe_mode
: boolean, default falserandom_seed
: integer, default nullA
safe_mode
option would be neat too: https://docs.mistral.ai/platform/guardrailingThe text was updated successfully, but these errors were encountered: