import { z } from 'zod';
/**
 * Upper bound for `reasoning_budget`. Mirrors the llm-llamacpp addon, which
 * stores the budget as a 32-bit `int` and rejects values above
 * `std::numeric_limits<int>::max()`.
 */
export declare const REASONING_BUDGET_MAX = 2147483647;
export declare const VERBOSITY: {
    readonly ERROR: 0;
    readonly WARN: 1;
    readonly INFO: 2;
    readonly DEBUG: 3;
};
export declare const llmConfigBaseSchema: z.ZodObject<{
    backend: z.ZodOptional<z.ZodArray<z.ZodEnum<{
        auto: "auto";
        cuda: "cuda";
        vulkan: "vulkan";
        metal: "metal";
        opencl: "opencl";
    }>>>;
    ctx_size: z.ZodOptional<z.ZodNumber>;
    temp: z.ZodOptional<z.ZodNumber>;
    top_p: z.ZodOptional<z.ZodNumber>;
    top_k: z.ZodOptional<z.ZodNumber>;
    seed: z.ZodOptional<z.ZodNumber>;
    gpu_layers: z.ZodOptional<z.ZodNumber>;
    lora: z.ZodOptional<z.ZodString>;
    device: z.ZodOptional<z.ZodString>;
    predict: z.ZodOptional<z.ZodUnion<readonly [z.ZodLiteral<-1>, z.ZodLiteral<-2>, z.ZodNumber]>>;
    system_prompt: z.ZodOptional<z.ZodString>;
    load_mode: z.ZodOptional<z.ZodEnum<{
        none: "none";
        mmap: "mmap";
        mlock: "mlock";
        "mmap+mlock": "mmap+mlock";
        dio: "dio";
    }>>;
    verbosity: z.ZodOptional<z.ZodEnum<{
        readonly ERROR: 0;
        readonly WARN: 1;
        readonly INFO: 2;
        readonly DEBUG: 3;
    }>>;
    presence_penalty: z.ZodOptional<z.ZodNumber>;
    frequency_penalty: z.ZodOptional<z.ZodNumber>;
    repeat_penalty: z.ZodOptional<z.ZodNumber>;
    stop_sequences: z.ZodOptional<z.ZodArray<z.ZodString>>;
    parallel: z.ZodOptional<z.ZodNumber>;
    tools: z.ZodOptional<z.ZodBoolean>;
    'cache-type-k': z.ZodOptional<z.ZodString>;
    'cache-type-v': z.ZodOptional<z.ZodString>;
    'main-gpu': z.ZodOptional<z.ZodUnion<readonly [z.ZodNumber, z.ZodEnum<{
        integrated: "integrated";
        dedicated: "dedicated";
    }>]>>;
    'rpc-servers': z.ZodOptional<z.ZodString>;
    devices: z.ZodOptional<z.ZodString>;
    'split-mode': z.ZodOptional<z.ZodEnum<{
        none: "none";
        layer: "layer";
        tensor: "tensor";
    }>>;
    'flash-attn': z.ZodOptional<z.ZodEnum<{
        auto: "auto";
        on: "on";
        off: "off";
    }>>;
    'tensor-split': z.ZodOptional<z.ZodString>;
    'batch-size': z.ZodOptional<z.ZodNumber>;
    'ubatch-size': z.ZodOptional<z.ZodNumber>;
    'cpu-moe': z.ZodOptional<z.ZodBoolean>;
    'n-cpu-moe': z.ZodOptional<z.ZodNumber>;
    'kv-offload': z.ZodOptional<z.ZodBoolean>;
    'image-max-tokens': z.ZodOptional<z.ZodNumber>;
    'image-min-tokens': z.ZodOptional<z.ZodNumber>;
    'image-max-megapixels': z.ZodOptional<z.ZodNumber>;
    threads: z.ZodOptional<z.ZodNumber>;
    'threads-batch': z.ZodOptional<z.ZodNumber>;
    'cpu-mask': z.ZodOptional<z.ZodString>;
    'cpu-mask-batch': z.ZodOptional<z.ZodString>;
    'override-tensor': z.ZodOptional<z.ZodString>;
    'n-cpu-ffn': z.ZodOptional<z.ZodNumber>;
    'moe-cache-mib': z.ZodOptional<z.ZodUnion<readonly [z.ZodNumber, z.ZodLiteral<"auto">]>>;
    'prefetch-weights': z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodLiteral<"auto">]>>;
    'tensor-read-lazy': z.ZodOptional<z.ZodEnum<{
        auto: "auto";
        on: "on";
        off: "off";
    }>>;
    fit: z.ZodOptional<z.ZodBoolean>;
    'fit-target': z.ZodOptional<z.ZodUnion<readonly [z.ZodNumber, z.ZodString]>>;
    'fit-ctx': z.ZodOptional<z.ZodNumber>;
    openclCacheDir: z.ZodOptional<z.ZodString>;
    reasoning_budget: z.ZodOptional<z.ZodNumber>;
    projectionModelSrc: z.ZodOptional<z.ZodUnion<readonly [z.ZodString, z.ZodObject<{
        src: z.ZodString;
        name: z.ZodOptional<z.ZodString>;
        modelId: z.ZodOptional<z.ZodString>;
        registryPath: z.ZodOptional<z.ZodString>;
        registrySource: z.ZodOptional<z.ZodString>;
        blobCoreKey: z.ZodOptional<z.ZodString>;
        blobIndex: z.ZodOptional<z.ZodNumber>;
        engine: z.ZodOptional<z.ZodString>;
        expectedSize: z.ZodOptional<z.ZodNumber>;
        sha256Checksum: z.ZodOptional<z.ZodString>;
        addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
            embeddings: "embeddings";
            diffusion: "diffusion";
            audiogen: "audiogen";
            tts: "tts";
            ocr: "ocr";
            vla: "vla";
            "llamacpp-completion": "llamacpp-completion";
            "whispercpp-transcription": "whispercpp-transcription";
            "bci-whispercpp-transcription": "bci-whispercpp-transcription";
            "llamacpp-embedding": "llamacpp-embedding";
            "llamacpp-decision": "llamacpp-decision";
            "nmtcpp-translation": "nmtcpp-translation";
            "onnx-tts": "onnx-tts";
            "tts-ggml": "tts-ggml";
            "parakeet-transcription": "parakeet-transcription";
            "moss-transcribe": "moss-transcribe";
            "ggml-ocr": "ggml-ocr";
            "sdcpp-generation": "sdcpp-generation";
            "audiogen-ggml": "audiogen-ggml";
            "ggml-vla": "ggml-vla";
            "ggml-classification": "ggml-classification";
            llm: "llm";
            whisper: "whisper";
            bci: "bci";
            nmt: "nmt";
            parakeet: "parakeet";
            classification: "classification";
        }>, z.ZodLiteral<"vad">]>>;
    }, z.core.$strip>]>>;
    image_tile_mode: z.ZodOptional<z.ZodEnum<{
        disabled: "disabled";
        batched: "batched";
        sequential: "sequential";
    }>>;
    image_no_upscale: z.ZodOptional<z.ZodEnum<{
        on: "on";
        off: "off";
    }>>;
    'mmproj-use-gpu': z.ZodOptional<z.ZodBoolean>;
}, z.core.$strip>;
export type LlmConfigInput = z.infer<typeof llmConfigBaseSchema>;
export declare const LLM_CONFIG_DEFAULTS: {
    readonly ctx_size: 1024;
    readonly device: "gpu";
    readonly system_prompt: "You are a helpful assistant.";
    readonly image_tile_mode: "sequential";
};
export declare const llmConfigSchema: z.ZodPipe<z.ZodObject<{
    backend: z.ZodOptional<z.ZodArray<z.ZodEnum<{
        auto: "auto";
        cuda: "cuda";
        vulkan: "vulkan";
        metal: "metal";
        opencl: "opencl";
    }>>>;
    ctx_size: z.ZodOptional<z.ZodNumber>;
    temp: z.ZodOptional<z.ZodNumber>;
    top_p: z.ZodOptional<z.ZodNumber>;
    top_k: z.ZodOptional<z.ZodNumber>;
    seed: z.ZodOptional<z.ZodNumber>;
    gpu_layers: z.ZodOptional<z.ZodNumber>;
    lora: z.ZodOptional<z.ZodString>;
    device: z.ZodOptional<z.ZodString>;
    predict: z.ZodOptional<z.ZodUnion<readonly [z.ZodLiteral<-1>, z.ZodLiteral<-2>, z.ZodNumber]>>;
    system_prompt: z.ZodOptional<z.ZodString>;
    load_mode: z.ZodOptional<z.ZodEnum<{
        none: "none";
        mmap: "mmap";
        mlock: "mlock";
        "mmap+mlock": "mmap+mlock";
        dio: "dio";
    }>>;
    verbosity: z.ZodOptional<z.ZodEnum<{
        readonly ERROR: 0;
        readonly WARN: 1;
        readonly INFO: 2;
        readonly DEBUG: 3;
    }>>;
    presence_penalty: z.ZodOptional<z.ZodNumber>;
    frequency_penalty: z.ZodOptional<z.ZodNumber>;
    repeat_penalty: z.ZodOptional<z.ZodNumber>;
    stop_sequences: z.ZodOptional<z.ZodArray<z.ZodString>>;
    parallel: z.ZodOptional<z.ZodNumber>;
    tools: z.ZodOptional<z.ZodBoolean>;
    'cache-type-k': z.ZodOptional<z.ZodString>;
    'cache-type-v': z.ZodOptional<z.ZodString>;
    'main-gpu': z.ZodOptional<z.ZodUnion<readonly [z.ZodNumber, z.ZodEnum<{
        integrated: "integrated";
        dedicated: "dedicated";
    }>]>>;
    'rpc-servers': z.ZodOptional<z.ZodString>;
    devices: z.ZodOptional<z.ZodString>;
    'split-mode': z.ZodOptional<z.ZodEnum<{
        none: "none";
        layer: "layer";
        tensor: "tensor";
    }>>;
    'flash-attn': z.ZodOptional<z.ZodEnum<{
        auto: "auto";
        on: "on";
        off: "off";
    }>>;
    'tensor-split': z.ZodOptional<z.ZodString>;
    'batch-size': z.ZodOptional<z.ZodNumber>;
    'ubatch-size': z.ZodOptional<z.ZodNumber>;
    'cpu-moe': z.ZodOptional<z.ZodBoolean>;
    'n-cpu-moe': z.ZodOptional<z.ZodNumber>;
    'kv-offload': z.ZodOptional<z.ZodBoolean>;
    'image-max-tokens': z.ZodOptional<z.ZodNumber>;
    'image-min-tokens': z.ZodOptional<z.ZodNumber>;
    'image-max-megapixels': z.ZodOptional<z.ZodNumber>;
    threads: z.ZodOptional<z.ZodNumber>;
    'threads-batch': z.ZodOptional<z.ZodNumber>;
    'cpu-mask': z.ZodOptional<z.ZodString>;
    'cpu-mask-batch': z.ZodOptional<z.ZodString>;
    'override-tensor': z.ZodOptional<z.ZodString>;
    'n-cpu-ffn': z.ZodOptional<z.ZodNumber>;
    'moe-cache-mib': z.ZodOptional<z.ZodUnion<readonly [z.ZodNumber, z.ZodLiteral<"auto">]>>;
    'prefetch-weights': z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodLiteral<"auto">]>>;
    'tensor-read-lazy': z.ZodOptional<z.ZodEnum<{
        auto: "auto";
        on: "on";
        off: "off";
    }>>;
    fit: z.ZodOptional<z.ZodBoolean>;
    'fit-target': z.ZodOptional<z.ZodUnion<readonly [z.ZodNumber, z.ZodString]>>;
    'fit-ctx': z.ZodOptional<z.ZodNumber>;
    openclCacheDir: z.ZodOptional<z.ZodString>;
    reasoning_budget: z.ZodOptional<z.ZodNumber>;
    projectionModelSrc: z.ZodOptional<z.ZodUnion<readonly [z.ZodString, z.ZodObject<{
        src: z.ZodString;
        name: z.ZodOptional<z.ZodString>;
        modelId: z.ZodOptional<z.ZodString>;
        registryPath: z.ZodOptional<z.ZodString>;
        registrySource: z.ZodOptional<z.ZodString>;
        blobCoreKey: z.ZodOptional<z.ZodString>;
        blobIndex: z.ZodOptional<z.ZodNumber>;
        engine: z.ZodOptional<z.ZodString>;
        expectedSize: z.ZodOptional<z.ZodNumber>;
        sha256Checksum: z.ZodOptional<z.ZodString>;
        addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
            embeddings: "embeddings";
            diffusion: "diffusion";
            audiogen: "audiogen";
            tts: "tts";
            ocr: "ocr";
            vla: "vla";
            "llamacpp-completion": "llamacpp-completion";
            "whispercpp-transcription": "whispercpp-transcription";
            "bci-whispercpp-transcription": "bci-whispercpp-transcription";
            "llamacpp-embedding": "llamacpp-embedding";
            "llamacpp-decision": "llamacpp-decision";
            "nmtcpp-translation": "nmtcpp-translation";
            "onnx-tts": "onnx-tts";
            "tts-ggml": "tts-ggml";
            "parakeet-transcription": "parakeet-transcription";
            "moss-transcribe": "moss-transcribe";
            "ggml-ocr": "ggml-ocr";
            "sdcpp-generation": "sdcpp-generation";
            "audiogen-ggml": "audiogen-ggml";
            "ggml-vla": "ggml-vla";
            "ggml-classification": "ggml-classification";
            llm: "llm";
            whisper: "whisper";
            bci: "bci";
            nmt: "nmt";
            parakeet: "parakeet";
            classification: "classification";
        }>, z.ZodLiteral<"vad">]>>;
    }, z.core.$strip>]>>;
    image_tile_mode: z.ZodOptional<z.ZodEnum<{
        disabled: "disabled";
        batched: "batched";
        sequential: "sequential";
    }>>;
    image_no_upscale: z.ZodOptional<z.ZodEnum<{
        on: "on";
        off: "off";
    }>>;
    'mmproj-use-gpu': z.ZodOptional<z.ZodBoolean>;
}, z.core.$strip>, z.ZodTransform<{
    backend?: ("auto" | "cuda" | "vulkan" | "metal" | "opencl")[] | undefined;
    ctx_size: number | undefined;
    temp?: number | undefined;
    top_p?: number | undefined;
    top_k?: number | undefined;
    seed?: number | undefined;
    gpu_layers?: number | undefined;
    lora?: string | undefined;
    device: string | undefined;
    predict?: number | undefined;
    system_prompt: string | undefined;
    load_mode?: "none" | "mmap" | "mlock" | "mmap+mlock" | "dio" | undefined;
    verbosity?: 0 | 3 | 2 | 1 | undefined;
    presence_penalty?: number | undefined;
    frequency_penalty?: number | undefined;
    repeat_penalty?: number | undefined;
    stop_sequences?: string[] | undefined;
    parallel?: number | undefined;
    tools?: boolean | undefined;
    'cache-type-k'?: string | undefined;
    'cache-type-v'?: string | undefined;
    'main-gpu'?: number | "integrated" | "dedicated" | undefined;
    'rpc-servers'?: string | undefined;
    devices?: string | undefined;
    'split-mode'?: "none" | "layer" | "tensor" | undefined;
    'flash-attn'?: "auto" | "on" | "off" | undefined;
    'tensor-split'?: string | undefined;
    'batch-size'?: number | undefined;
    'ubatch-size'?: number | undefined;
    'cpu-moe'?: boolean | undefined;
    'n-cpu-moe'?: number | undefined;
    'kv-offload'?: boolean | undefined;
    'image-max-tokens'?: number | undefined;
    'image-min-tokens'?: number | undefined;
    'image-max-megapixels'?: number | undefined;
    threads?: number | undefined;
    'threads-batch'?: number | undefined;
    'cpu-mask'?: string | undefined;
    'cpu-mask-batch'?: string | undefined;
    'override-tensor'?: string | undefined;
    'n-cpu-ffn'?: number | undefined;
    'moe-cache-mib'?: number | "auto" | undefined;
    'prefetch-weights'?: boolean | "auto" | undefined;
    'tensor-read-lazy'?: "auto" | "on" | "off" | undefined;
    fit?: boolean | undefined;
    'fit-target'?: string | number | undefined;
    'fit-ctx'?: number | undefined;
    openclCacheDir?: string | undefined;
    reasoning_budget?: number | undefined;
    projectionModelSrc?: string | {
        src: string;
        name?: string | undefined;
        modelId?: string | undefined;
        registryPath?: string | undefined;
        registrySource?: string | undefined;
        blobCoreKey?: string | undefined;
        blobIndex?: number | undefined;
        engine?: string | undefined;
        expectedSize?: number | undefined;
        sha256Checksum?: string | undefined;
        addon?: "embeddings" | "diffusion" | "audiogen" | "tts" | "ocr" | "vla" | "llamacpp-completion" | "whispercpp-transcription" | "bci-whispercpp-transcription" | "llamacpp-embedding" | "llamacpp-decision" | "nmtcpp-translation" | "onnx-tts" | "tts-ggml" | "parakeet-transcription" | "moss-transcribe" | "ggml-ocr" | "sdcpp-generation" | "audiogen-ggml" | "ggml-vla" | "ggml-classification" | "llm" | "whisper" | "bci" | "nmt" | "parakeet" | "classification" | "vad" | undefined;
    } | undefined;
    image_tile_mode: "disabled" | "batched" | "sequential" | undefined;
    image_no_upscale?: "on" | "off" | undefined;
    'mmproj-use-gpu'?: boolean | undefined;
}, {
    backend?: ("auto" | "cuda" | "vulkan" | "metal" | "opencl")[] | undefined;
    ctx_size?: number | undefined;
    temp?: number | undefined;
    top_p?: number | undefined;
    top_k?: number | undefined;
    seed?: number | undefined;
    gpu_layers?: number | undefined;
    lora?: string | undefined;
    device?: string | undefined;
    predict?: number | undefined;
    system_prompt?: string | undefined;
    load_mode?: "none" | "mmap" | "mlock" | "mmap+mlock" | "dio" | undefined;
    verbosity?: 0 | 3 | 2 | 1 | undefined;
    presence_penalty?: number | undefined;
    frequency_penalty?: number | undefined;
    repeat_penalty?: number | undefined;
    stop_sequences?: string[] | undefined;
    parallel?: number | undefined;
    tools?: boolean | undefined;
    'cache-type-k'?: string | undefined;
    'cache-type-v'?: string | undefined;
    'main-gpu'?: number | "integrated" | "dedicated" | undefined;
    'rpc-servers'?: string | undefined;
    devices?: string | undefined;
    'split-mode'?: "none" | "layer" | "tensor" | undefined;
    'flash-attn'?: "auto" | "on" | "off" | undefined;
    'tensor-split'?: string | undefined;
    'batch-size'?: number | undefined;
    'ubatch-size'?: number | undefined;
    'cpu-moe'?: boolean | undefined;
    'n-cpu-moe'?: number | undefined;
    'kv-offload'?: boolean | undefined;
    'image-max-tokens'?: number | undefined;
    'image-min-tokens'?: number | undefined;
    'image-max-megapixels'?: number | undefined;
    threads?: number | undefined;
    'threads-batch'?: number | undefined;
    'cpu-mask'?: string | undefined;
    'cpu-mask-batch'?: string | undefined;
    'override-tensor'?: string | undefined;
    'n-cpu-ffn'?: number | undefined;
    'moe-cache-mib'?: number | "auto" | undefined;
    'prefetch-weights'?: boolean | "auto" | undefined;
    'tensor-read-lazy'?: "auto" | "on" | "off" | undefined;
    fit?: boolean | undefined;
    'fit-target'?: string | number | undefined;
    'fit-ctx'?: number | undefined;
    openclCacheDir?: string | undefined;
    reasoning_budget?: number | undefined;
    projectionModelSrc?: string | {
        src: string;
        name?: string | undefined;
        modelId?: string | undefined;
        registryPath?: string | undefined;
        registrySource?: string | undefined;
        blobCoreKey?: string | undefined;
        blobIndex?: number | undefined;
        engine?: string | undefined;
        expectedSize?: number | undefined;
        sha256Checksum?: string | undefined;
        addon?: "embeddings" | "diffusion" | "audiogen" | "tts" | "ocr" | "vla" | "llamacpp-completion" | "whispercpp-transcription" | "bci-whispercpp-transcription" | "llamacpp-embedding" | "llamacpp-decision" | "nmtcpp-translation" | "onnx-tts" | "tts-ggml" | "parakeet-transcription" | "moss-transcribe" | "ggml-ocr" | "sdcpp-generation" | "audiogen-ggml" | "ggml-vla" | "ggml-classification" | "llm" | "whisper" | "bci" | "nmt" | "parakeet" | "classification" | "vad" | undefined;
    } | undefined;
    image_tile_mode?: "disabled" | "batched" | "sequential" | undefined;
    image_no_upscale?: "on" | "off" | undefined;
    'mmproj-use-gpu'?: boolean | undefined;
}>>;
export type LlmConfig = z.infer<typeof llmConfigSchema>;
export declare const embedConfigBaseSchema: z.ZodObject<{
    backend: z.ZodOptional<z.ZodArray<z.ZodEnum<{
        auto: "auto";
        cuda: "cuda";
        vulkan: "vulkan";
        metal: "metal";
        opencl: "opencl";
    }>>>;
    gpuLayers: z.ZodOptional<z.ZodNumber>;
    device: z.ZodOptional<z.ZodEnum<{
        cpu: "cpu";
        gpu: "gpu";
    }>>;
    batchSize: z.ZodOptional<z.ZodNumber>;
    pooling: z.ZodOptional<z.ZodEnum<{
        none: "none";
        mean: "mean";
        cls: "cls";
        last: "last";
        rank: "rank";
    }>>;
    attention: z.ZodOptional<z.ZodEnum<{
        causal: "causal";
        "non-causal": "non-causal";
    }>>;
    embdNormalize: z.ZodOptional<z.ZodNumber>;
    flashAttention: z.ZodOptional<z.ZodEnum<{
        auto: "auto";
        on: "on";
        off: "off";
    }>>;
    mainGpu: z.ZodOptional<z.ZodUnion<readonly [z.ZodNumber, z.ZodEnum<{
        integrated: "integrated";
        dedicated: "dedicated";
    }>]>>;
    splitMode: z.ZodOptional<z.ZodEnum<{
        none: "none";
        layer: "layer";
    }>>;
    tensorSplit: z.ZodOptional<z.ZodString>;
    verbosity: z.ZodOptional<z.ZodEnum<{
        readonly ERROR: 0;
        readonly WARN: 1;
        readonly INFO: 2;
        readonly DEBUG: 3;
    }>>;
    openclCacheDir: z.ZodOptional<z.ZodString>;
}, z.core.$strip>;
export type EmbedConfigInput = z.infer<typeof embedConfigBaseSchema>;
export declare const EMBED_CONFIG_DEFAULTS: {
    readonly gpuLayers: 99;
    readonly device: "gpu";
    readonly batchSize: 1024;
};
export declare const embedConfigSchema: z.ZodPipe<z.ZodObject<{
    backend: z.ZodOptional<z.ZodArray<z.ZodEnum<{
        auto: "auto";
        cuda: "cuda";
        vulkan: "vulkan";
        metal: "metal";
        opencl: "opencl";
    }>>>;
    gpuLayers: z.ZodOptional<z.ZodNumber>;
    device: z.ZodOptional<z.ZodEnum<{
        cpu: "cpu";
        gpu: "gpu";
    }>>;
    batchSize: z.ZodOptional<z.ZodNumber>;
    pooling: z.ZodOptional<z.ZodEnum<{
        none: "none";
        mean: "mean";
        cls: "cls";
        last: "last";
        rank: "rank";
    }>>;
    attention: z.ZodOptional<z.ZodEnum<{
        causal: "causal";
        "non-causal": "non-causal";
    }>>;
    embdNormalize: z.ZodOptional<z.ZodNumber>;
    flashAttention: z.ZodOptional<z.ZodEnum<{
        auto: "auto";
        on: "on";
        off: "off";
    }>>;
    mainGpu: z.ZodOptional<z.ZodUnion<readonly [z.ZodNumber, z.ZodEnum<{
        integrated: "integrated";
        dedicated: "dedicated";
    }>]>>;
    splitMode: z.ZodOptional<z.ZodEnum<{
        none: "none";
        layer: "layer";
    }>>;
    tensorSplit: z.ZodOptional<z.ZodString>;
    verbosity: z.ZodOptional<z.ZodEnum<{
        readonly ERROR: 0;
        readonly WARN: 1;
        readonly INFO: 2;
        readonly DEBUG: 3;
    }>>;
    openclCacheDir: z.ZodOptional<z.ZodString>;
}, z.core.$strip>, z.ZodTransform<{
    backend?: ("auto" | "cuda" | "vulkan" | "metal" | "opencl")[] | undefined;
    gpuLayers: number | undefined;
    device: "cpu" | "gpu" | undefined;
    batchSize: number | undefined;
    pooling?: "none" | "mean" | "cls" | "last" | "rank" | undefined;
    attention?: "causal" | "non-causal" | undefined;
    embdNormalize?: number | undefined;
    flashAttention?: "auto" | "on" | "off" | undefined;
    mainGpu?: number | "integrated" | "dedicated" | undefined;
    splitMode?: "none" | "layer" | undefined;
    tensorSplit?: string | undefined;
    verbosity?: 0 | 3 | 2 | 1 | undefined;
    openclCacheDir?: string | undefined;
}, {
    backend?: ("auto" | "cuda" | "vulkan" | "metal" | "opencl")[] | undefined;
    gpuLayers?: number | undefined;
    device?: "cpu" | "gpu" | undefined;
    batchSize?: number | undefined;
    pooling?: "none" | "mean" | "cls" | "last" | "rank" | undefined;
    attention?: "causal" | "non-causal" | undefined;
    embdNormalize?: number | undefined;
    flashAttention?: "auto" | "on" | "off" | undefined;
    mainGpu?: number | "integrated" | "dedicated" | undefined;
    splitMode?: "none" | "layer" | undefined;
    tensorSplit?: string | undefined;
    verbosity?: 0 | 3 | 2 | 1 | undefined;
    openclCacheDir?: string | undefined;
}>>;
export type EmbedConfig = z.infer<typeof embedConfigSchema>;