Table of Contents

Class OllamaReplyOptions

Namespace
AutoGen.Ollama
Assembly
AutoGen.Ollama.dll
public class OllamaReplyOptions : GenerateReplyOptions
Inheritance
OllamaReplyOptions
Inherited Members

Properties

Format

the format to return a response in. Currently, the only accepted value is json

public FormatType Format { get; set; }

Property Value

FormatType

KeepAlive

controls how long the model will stay loaded into memory following the request (default: 5m)

public string? KeepAlive { get; set; }

Property Value

string

MaxToken

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

public int? MaxToken { get; set; }

Property Value

int?

MiroStat

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

public int? MiroStat { get; set; }

Property Value

int?

MiroStatEta

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)

public float? MiroStatEta { get; set; }

Property Value

float?

MiroStatTau

Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)

public float? MiroStatTau { get; set; }

Property Value

float?

NumCtx

Sets the size of the context window used to generate the next token. (Default: 2048)

public int? NumCtx { get; set; }

Property Value

int?

NumGpu

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

public int? NumGpu { get; set; }

Property Value

int?

NumGqa

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

public int? NumGqa { get; set; }

Property Value

int?

NumThread

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).

public int? NumThread { get; set; }

Property Value

int?

RepeatLastN

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

public int? RepeatLastN { get; set; }

Property Value

int?

RepeatPenalty

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)

public float? RepeatPenalty { get; set; }

Property Value

float?

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)

public int? Seed { get; set; }

Property Value

int?

Temperature

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

public float? Temperature { get; set; }

Property Value

float?

Template

the prompt template to use (overrides what is defined in the Modelfile)

public string? Template { get; set; }

Property Value

string

TfsZ

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)

public float? TfsZ { get; set; }

Property Value

float?

TopK

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)

public int? TopK { get; set; }

Property Value

int?

TopP

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)

public int? TopP { get; set; }

Property Value

int?