@Generated(value="OracleSDKGenerator",
comments="API Version: 20231130")
public final class CohereLlmInferenceRequest
extends LlmInferenceRequest
Details for the text generation request for Cohere models.
Note: Objects should always be created or deserialized using the CohereLlmInferenceRequest.Builder. This model
distinguishes fields that are null because they are unset from fields that are explicitly
set to null. This is done in the setter methods of the CohereLlmInferenceRequest.Builder, which maintain a
set of all explicitly set fields called CohereLlmInferenceRequest.Builder.__explicitlySet__. The hashCode() and equals(Object) methods are implemented to take the explicitly set
fields into account. The constructor, on the other hand, does not take the explicitly set fields
into account (since the constructor cannot distinguish explicit null from unset null).
| Modifier and Type | Class and Description |
|---|---|
static class |
CohereLlmInferenceRequest.Builder |
static class |
CohereLlmInferenceRequest.ReturnLikelihoods
Specifies how and if the token likelihoods are returned with the response.
|
static class |
CohereLlmInferenceRequest.Truncate
For an input that’s longer than the maximum token length, specifies which part of the input
text will be truncated.
|
LlmInferenceRequest.RuntimeTypeEXPLICITLY_SET_FILTER_NAME, EXPLICITLY_SET_PROPERTY_NAME| Constructor and Description |
|---|
CohereLlmInferenceRequest(String prompt,
Boolean isStream,
Integer numGenerations,
Boolean isEcho,
Integer maxTokens,
Double temperature,
Integer topK,
Double topP,
Double frequencyPenalty,
Double presencePenalty,
List<String> stopSequences,
CohereLlmInferenceRequest.ReturnLikelihoods returnLikelihoods,
CohereLlmInferenceRequest.Truncate truncate)
Deprecated.
|
| Modifier and Type | Method and Description |
|---|---|
static CohereLlmInferenceRequest.Builder |
builder()
Create a new builder.
|
boolean |
equals(Object o) |
Double |
getFrequencyPenalty()
To reduce repetitiveness of generated tokens, this number penalizes new tokens based on their
frequency in the generated text so far.
|
Boolean |
getIsEcho()
Whether or not to return the user prompt in the response.
|
Boolean |
getIsStream()
Whether to stream back partial progress.
|
Integer |
getMaxTokens()
The maximum number of tokens to predict for each response.
|
Integer |
getNumGenerations()
The number of generated texts that will be returned.
|
Double |
getPresencePenalty()
To reduce repetitiveness of generated tokens, this number penalizes new tokens based on
whether they’ve appeared in the generated text so far.
|
String |
getPrompt()
Represents the prompt to be completed.
|
CohereLlmInferenceRequest.ReturnLikelihoods |
getReturnLikelihoods()
Specifies how and if the token likelihoods are returned with the response.
|
List<String> |
getStopSequences()
The generated text is cut at the end of the earliest occurrence of this stop sequence.
|
Double |
getTemperature()
A number that sets the randomness of the generated output.
|
Integer |
getTopK()
An integer that sets up the model to use only the top k most likely tokens in the generated
output.
|
Double |
getTopP()
If set to a probability 0.0 < p < 1.0, it ensures that only the most likely tokens, with
total probability mass of p, are considered for generation at each step.
|
CohereLlmInferenceRequest.Truncate |
getTruncate()
For an input that’s longer than the maximum token length, specifies which part of the input
text will be truncated.
|
int |
hashCode() |
CohereLlmInferenceRequest.Builder |
toBuilder() |
String |
toString() |
String |
toString(boolean includeByteArrayContents)
Return a string representation of the object.
|
markPropertyAsExplicitlySet, wasPropertyExplicitlySet@Deprecated public CohereLlmInferenceRequest(String prompt, Boolean isStream, Integer numGenerations, Boolean isEcho, Integer maxTokens, Double temperature, Integer topK, Double topP, Double frequencyPenalty, Double presencePenalty, List<String> stopSequences, CohereLlmInferenceRequest.ReturnLikelihoods returnLikelihoods, CohereLlmInferenceRequest.Truncate truncate)
public static CohereLlmInferenceRequest.Builder builder()
Create a new builder.
public CohereLlmInferenceRequest.Builder toBuilder()
public String getPrompt()
Represents the prompt to be completed. The trailing white spaces are trimmed before completion.
public Boolean getIsStream()
Whether to stream back partial progress. If set, tokens are sent as data-only server-sent events as they become available.
public Integer getNumGenerations()
The number of generated texts that will be returned.
public Boolean getIsEcho()
Whether or not to return the user prompt in the response. This option only applies to non-stream results.
public Integer getMaxTokens()
The maximum number of tokens to predict for each response. Includes input plus output tokens.
public Double getTemperature()
A number that sets the randomness of the generated output. A lower temperature means a less random generations.
Use lower numbers for tasks with a correct answer such as question answering or summarizing. High temperatures can generate hallucinations or factually incorrect information. Start with temperatures lower than 1.0 and increase the temperature for more creative outputs, as you regenerate the prompts to refine the outputs.
public Integer getTopK()
An integer that sets up the model to use only the top k most likely tokens in the generated output. A higher k introduces more randomness into the output making the output text sound more natural. Default value is 0 which disables this method and considers all tokens. To set a number for the likely tokens, choose an integer between 1 and 500.
If also using top p, then the model considers only the top tokens whose probabilities add up to p percent and ignores the rest of the k tokens. For example, if k is 20, but the probabilities of the top 10 add up to .75, then only the top 10 tokens are chosen.
public Double getTopP()
If set to a probability 0.0 < p < 1.0, it ensures that only the most likely tokens, with total probability mass of p, are considered for generation at each step.
To eliminate tokens with low likelihood, assign p a minimum percentage for the next token's likelihood. For example, when p is set to 0.75, the model eliminates the bottom 25 percent for the next token. Set to 1.0 to consider all tokens and set to 0 to disable. If both k and p are enabled, p acts after k.
public Double getFrequencyPenalty()
To reduce repetitiveness of generated tokens, this number penalizes new tokens based on their frequency in the generated text so far. Greater numbers encourage the model to use new tokens, while lower numbers encourage the model to repeat the tokens. Set to 0 to disable.
public Double getPresencePenalty()
To reduce repetitiveness of generated tokens, this number penalizes new tokens based on whether they’ve appeared in the generated text so far. Greater numbers encourage the model to use new tokens, while lower numbers encourage the model to repeat the tokens.
Similar to frequency penalty, a penalty is applied to previously present tokens, except that this penalty is applied equally to all tokens that have already appeared, regardless of how many times they've appeared. Set to 0 to disable.
public List<String> getStopSequences()
The generated text is cut at the end of the earliest occurrence of this stop sequence. The generated text will include this stop sequence.
public CohereLlmInferenceRequest.ReturnLikelihoods getReturnLikelihoods()
Specifies how and if the token likelihoods are returned with the response.
public CohereLlmInferenceRequest.Truncate getTruncate()
For an input that’s longer than the maximum token length, specifies which part of the input text will be truncated.
public String toString()
toString in class LlmInferenceRequestpublic String toString(boolean includeByteArrayContents)
Return a string representation of the object.
toString in class LlmInferenceRequestincludeByteArrayContents - true to include the full contents of byte arrayspublic boolean equals(Object o)
equals in class LlmInferenceRequestpublic int hashCode()
hashCode in class LlmInferenceRequestCopyright © 2016–2024. All rights reserved.