nodes/generated

Interface LmChatNvidiaNodeParameters

Source
interface LmChatNvidiaNodeParameters {
    model?:
        | "nvidia/llama-3.3-nemotron-super-49b-v1"
        | "nvidia/llama-3.1-nemotron-70b-instruct"
        | "nvidia/llama-3.1-nemotron-nano-8b-v1"
        | "nvidia/nemotron-4-340b-instruct"
        | "nvidia/nemotron-mini-4b-instruct";
    options?: {
        frequencyPenalty?: number;
        maxRetries?: number;
        maxTokens?: number;
        presencePenalty?: number;
        responseFormat?: "text"
        | "json_object";
        temperature?: number;
        timeout?: number;
        topP?: number;
    };
}

Properties§

§readonly model?:
    | "nvidia/llama-3.3-nemotron-super-49b-v1"
    | "nvidia/llama-3.1-nemotron-70b-instruct"
    | "nvidia/llama-3.1-nemotron-nano-8b-v1"
    | "nvidia/nemotron-4-340b-instruct"
    | "nvidia/nemotron-mini-4b-instruct"

The Nemotron model which will generate the completion. Learn more. Default: "nvidia/llama-3.3-nemotron-super-49b-v1" Type options: {"loadOptions":{"routing":{"request":{"method":"GET","url":"/models"},"output":{"postReceive":[{"type":"rootProperty","properties":{"property":"data"}},{"type":"filter","properties":{"pass":"={{ /nemotron/i.test($responseItem.id) }}"}},{"type":"setKeyValue","properties":{"name":"={{$responseItem.id}}","value":"={{$responseItem.id}}"}},{"type":"sort","properties":{"key":"name"}}]}}}}

§readonly options?: { ... }

Additional options to add Default: {}