mirror of
https://github.com/ollama/ollama.git
synced 2025-03-24 16:51:57 +01:00
93 lines
2.7 KiB
C++
Vendored
93 lines
2.7 KiB
C++
Vendored
/**
|
|
* 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-impl.h"
|
|
#include "llama-hparams.h"
|
|
|
|
#include "ggml-cpp.h"
|
|
|
|
#include <unordered_map>
|
|
#include <vector>
|
|
|
|
//
|
|
// llama_adapter_cvec
|
|
//
|
|
|
|
// TODO: rename to llama_adapter_cvec
|
|
struct llama_control_vector {
|
|
std::vector<ggml_context_ptr> ctxs;
|
|
std::vector<ggml_backend_buffer_ptr> bufs;
|
|
|
|
std::vector<struct ggml_tensor *> tensors; // per layer
|
|
|
|
int32_t layer_start = -1;
|
|
int32_t layer_end = -1;
|
|
|
|
struct ggml_tensor * tensor_for(int il) const;
|
|
|
|
struct ggml_tensor * apply_to(struct ggml_context * ctx, struct ggml_tensor * cur, int il) const;
|
|
};
|
|
|
|
int32_t llama_control_vector_apply(
|
|
struct llama_control_vector & cvec,
|
|
const llama_model & model,
|
|
const float * data,
|
|
size_t len,
|
|
int32_t n_embd,
|
|
int32_t il_start,
|
|
int32_t il_end);
|
|
|
|
//
|
|
// llama_adapter_lora
|
|
//
|
|
|
|
// TODO: rename to llama_adapter_lora_weight
|
|
struct llama_lora_weight {
|
|
struct ggml_tensor * a = nullptr;
|
|
struct ggml_tensor * b = nullptr;
|
|
|
|
llama_lora_weight() = default;
|
|
llama_lora_weight(struct ggml_tensor * a, struct ggml_tensor * b) : a(a), b(b) {}
|
|
};
|
|
|
|
// TODO: rename to llama_adapter_lora
|
|
struct llama_lora_adapter {
|
|
// map tensor name to lora_a_b
|
|
std::unordered_map<std::string, struct llama_lora_weight> ab_map;
|
|
|
|
std::vector<ggml_context_ptr> ctxs;
|
|
std::vector<ggml_backend_buffer_ptr> bufs;
|
|
|
|
float alpha;
|
|
|
|
llama_lora_adapter() = default;
|
|
~llama_lora_adapter() = default;
|
|
|
|
llama_lora_weight * get_weight(struct ggml_tensor * w);
|
|
};
|