view release on metacpan or  search on metacpan

lib/AI/Ollama/RequestOptions.pm  view on Meta::CPAN

has 'temperature' => (
    is       => 'ro',
    isa      => Num,
);

=head2 C<< 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)

=cut

has 'tfs_z' => (
    is       => 'ro',
    isa      => Num,
);

=head2 C<< 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)

=cut

has 'top_k' => (
    is       => 'ro',
    isa      => Int,
);

=head2 C<< 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)

=cut

has 'top_p' => (
    is       => 'ro',
    isa      => Num,
);

=head2 C<< typical_p >>

Typical p is used to reduce the impact of less probable tokens from the output.

=cut

has 'typical_p' => (
    is       => 'ro',
    isa      => Num,
);

=head2 C<< use_mlock >>

Enable mlock. (Default: false)

=cut

has 'use_mlock' => (
    is       => 'ro',
);

=head2 C<< use_mmap >>

Enable mmap. (Default: false)

=cut

has 'use_mmap' => (
    is       => 'ro',
);

=head2 C<< vocab_only >>

Enable vocab only. (Default: false)

=cut

has 'vocab_only' => (
    is       => 'ro',
);


1;