File Coverage

blib/lib/AI/Ollama/RequestOptions.pm

Criterion	Covered	Total	%
statement	20	24	83.3
branch			n/a
condition			n/a
subroutine	7	8	87.5
pod	0	1	0.0
total	27	33	81.8

package AI::Ollama::RequestOptions 0.05;
# DO NOT EDIT! This is an autogenerated file.

use 5.020;
use Moo 2;
use experimental 'signatures';
use stable 'postderef';
use Types::Standard qw(Enum Str Bool Num Int HashRef ArrayRef);
use MooX::TypeTiny;

use namespace::clean;

=encoding utf8

=head1 NAME

AI::Ollama::RequestOptions -

=head1 SYNOPSIS

  my $obj = AI::Ollama::RequestOptions->new();
  ...

=cut

sub as_hash( $self ) {
    return { $self->%* }
}

=head1 PROPERTIES

=head2 C<< embedding_only >>

Enable embedding only. (Default: false)

=cut

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

=head2 C<< f16_kv >>

Enable f16 key/value. (Default: false)

=cut

has 'f16_kv' => (
    is       => 'ro',
);

=head2 C<< frequency_penalty >>

Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

=cut

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

=head2 C<< logits_all >>

Enable logits all. (Default: false)

=cut

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

=head2 C<< low_vram >>

Enable low VRAM mode. (Default: false)

=cut

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

=head2 C<< main_gpu >>

The GPU to use for the main model. Default is 0.

=cut

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

=head2 C<< mirostat >>

Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)

=cut

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

=head2 C<< 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)

=cut

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

=head2 C<< 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)

=cut

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

=head2 C<< num_batch >>

Sets the number of batches to use for generation. (Default: 1)

=cut

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

=head2 C<< num_ctx >>

Sets the size of the context window used to generate the next token.

=cut

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

=head2 C<< num_gpu >>

The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable.

=cut

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

=head2 C<< num_gqa >>

The number of GQA groups in the transformer layer. Required for some models, for example it is 8 for `llama2:70b`.

=cut

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

=head2 C<< num_keep >>

Number of tokens to keep from the prompt.

=cut

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

=head2 C<< num_predict >>

Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context)

=cut

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

=head2 C<< 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).

=cut

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

=head2 C<< numa >>

Enable NUMA support. (Default: false)

=cut

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

=head2 C<< penalize_newline >>

Penalize newlines in the output. (Default: false)

=cut

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

=head2 C<< presence_penalty >>

Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

=cut

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

=head2 C<< repeat_last_n >>

Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)

=cut

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

=head2 C<< 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)

=cut

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

=head2 C<< rope_frequency_base >>

The base of the rope frequency scale. (Default: 1.0)

=cut

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

=head2 C<< rope_frequency_scale >>

The scale of the rope frequency. (Default: 1.0)

=cut

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

=head2 C<< seed >>

Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0)

=cut

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

=head2 C<< stop >>

Sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

=cut

has 'stop' => (
    is       => 'ro',
    isa      => ArrayRef[Str],
);

=head2 C<< temperature >>

The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)

=cut

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;