ollama/llama/llama-cparams.h

/**
 * llama.cpp - commit 46e3556e01b824e52395fb050b29804b6cff2a7c - do not edit this file
 *
 * MIT License
 *
 * Copyright (c) 2023-2024 The ggml authors
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in all
 * copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#pragma once

#include "llama.h"

#include <cstdint>

struct llama_cparams {
    uint32_t n_ctx;           // context size used during inference
    uint32_t n_batch;
    uint32_t n_ubatch;
    uint32_t n_seq_max;
    int      n_threads;       // number of threads to use for generation
    int      n_threads_batch; // number of threads to use for batch processing

    float rope_freq_base;
    float rope_freq_scale;

    uint32_t n_ctx_orig_yarn;
    // These hyperparameters are not exposed in GGUF, because all
    // existing YaRN models use the same values for them.
    float yarn_ext_factor;
    float yarn_attn_factor;
    float yarn_beta_fast;
    float yarn_beta_slow;
    float defrag_thold;

    bool embeddings;
    bool causal_attn;
    bool offload_kqv;
    bool flash_attn;
    bool no_perf;
    bool cross_attn;

    enum llama_pooling_type pooling_type;

    ggml_backend_sched_eval_callback cb_eval;
    void * cb_eval_user_data;
};