Package com.oracle.bmc.generativeaiinference.model

Class LlamaLlmInferenceRequest.Builder

    • Constructor Detail

      • Builder

        public Builder()

    • Method Detail

      • prompt

        public LlamaLlmInferenceRequest.Builder prompt​(String prompt)
        Represents the prompt to be completed.

        The trailing white spaces are trimmed before completion.

        Parameters:
        prompt - the value to set
        Returns:
        this builder

      • isStream

        public LlamaLlmInferenceRequest.Builder isStream​(Boolean isStream)
        Whether to stream back partial progress.

        If set, tokens are sent as data-only server-sent events as they become available.

        Parameters:
        isStream - the value to set
        Returns:
        this builder

      • numGenerations

        public LlamaLlmInferenceRequest.Builder numGenerations​(Integer numGenerations)
        The number of of generated texts that will be returned.
        Parameters:
        numGenerations - the value to set
        Returns:
        this builder

      • isEcho

        public LlamaLlmInferenceRequest.Builder isEcho​(Boolean isEcho)
        Whether or not to return the user prompt in the response.

        Applies only to non-stream results.

        Parameters:
        isEcho - the value to set
        Returns:
        this builder

      • topK

        public LlamaLlmInferenceRequest.Builder topK​(Integer topK)
        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 -1 which means to consider all tokens. Setting to 0 disables this method and considers all tokens.

        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.

        Parameters:
        topK - the value to set
        Returns:
        this builder

      • topP

        public LlamaLlmInferenceRequest.Builder topP​(Double topP)
        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 to consider all tokens and set to 0 to disable. If both k and p are enabled, p acts after k.

        Parameters:
        topP - the value to set
        Returns:
        this builder

      • temperature

        public LlamaLlmInferenceRequest.Builder temperature​(Double temperature)
        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.

        Parameters:
        temperature - the value to set
        Returns:
        this builder

      • frequencyPenalty

        public LlamaLlmInferenceRequest.Builder frequencyPenalty​(Double frequencyPenalty)
        To reduce repetitiveness of generated tokens, this number penalizes new tokens based on their frequency in the generated text so far.

        Values > 0 encourage the model to use new tokens and values < 0 encourage the model to repeat tokens. Set to 0 to disable.

        Parameters:
        frequencyPenalty - the value to set
        Returns:
        this builder

      • presencePenalty

        public LlamaLlmInferenceRequest.Builder presencePenalty​(Double presencePenalty)
        To reduce repetitiveness of generated tokens, this number penalizes new tokens based on whether they’ve appeared in the generated text so far.

        Values > 0 encourage the model to use new tokens and values < 0 encourage the model to repeat 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.

        Parameters:
        presencePenalty - the value to set
        Returns:
        this builder

      • stop

        public LlamaLlmInferenceRequest.Builder stop​(List<String> stop)
        List of strings that stop the generation if they are generated for the response text.

        The returned output will not contain the stop strings.

        Parameters:
        stop - the value to set
        Returns:
        this builder

      • logProbs

        public LlamaLlmInferenceRequest.Builder logProbs​(Integer logProbs)
        Includes the logarithmic probabilities for the most likely output tokens and the chosen tokens.

        For example, if the log probability is 5, the API returns a list of the 5 most likely tokens. The API returns the log probability of the sampled token, so there might be up to logprobs+1 elements in the response.

        Parameters:
        logProbs - the value to set
        Returns:
        this builder

      • maxTokens

        public LlamaLlmInferenceRequest.Builder maxTokens​(Integer maxTokens)
        The maximum number of tokens that can be generated per output sequence.

        The token count of the prompt plus maxTokens cannot exceed the model’s context length.

        Parameters:
        maxTokens - the value to set
        Returns:
        this builder