mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-27 20:04:35 +00:00
10f19c1121
* set default n_batch to 512 when using BLAS * spacing * alternate implementation of setting different n_batch for BLAS * set n_batch to 512 for all cases
99 lines
3.3 KiB
C++
99 lines
3.3 KiB
C++
// Various helper functions and utilities
|
|
|
|
#pragma once
|
|
|
|
#include "llama.h"
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
#include <random>
|
|
#include <thread>
|
|
|
|
//
|
|
// CLI argument parsing
|
|
//
|
|
|
|
struct gpt_params {
|
|
int32_t seed = -1; // RNG seed
|
|
int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
|
|
int32_t n_predict = 128; // new tokens to predict
|
|
int32_t repeat_last_n = 64; // last n tokens to penalize
|
|
int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions)
|
|
int32_t n_ctx = 512; // context size
|
|
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
|
|
int32_t n_keep = 0; // number of tokens to keep from initial prompt
|
|
|
|
// sampling parameters
|
|
int32_t top_k = 40;
|
|
float top_p = 0.95f;
|
|
float temp = 0.80f;
|
|
float repeat_penalty = 1.10f;
|
|
|
|
std::string model = "models/lamma-7B/ggml-model.bin"; // model path
|
|
std::string prompt = "";
|
|
std::string input_prefix = ""; // string to prefix user inputs with
|
|
std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
|
|
|
|
std::string lora_adapter = ""; // lora adapter path
|
|
std::string lora_base = ""; // base model path for the lora adapter
|
|
|
|
bool memory_f16 = true; // use f16 instead of f32 for memory kv
|
|
bool random_prompt = false; // do not randomize prompt if none provided
|
|
bool use_color = false; // use color to distinguish generations and inputs
|
|
bool interactive = false; // interactive mode
|
|
|
|
bool embedding = false; // get only sentence embedding
|
|
bool interactive_start = false; // wait for user input immediately
|
|
|
|
bool instruct = false; // instruction mode (used for Alpaca models)
|
|
bool ignore_eos = false; // do not stop generating after eos
|
|
bool perplexity = false; // compute perplexity over the prompt
|
|
bool use_mmap = true; // use mmap for faster loads
|
|
bool use_mlock = false; // use mlock to keep model in memory
|
|
bool mem_test = false; // compute maximum memory usage
|
|
bool verbose_prompt = false; // print prompt tokens before generation
|
|
};
|
|
|
|
bool gpt_params_parse(int argc, char ** argv, gpt_params & params);
|
|
|
|
void gpt_print_usage(int argc, char ** argv, const gpt_params & params);
|
|
|
|
std::string gpt_random_prompt(std::mt19937 & rng);
|
|
|
|
//
|
|
// Vocab utils
|
|
//
|
|
|
|
std::vector<llama_token> llama_tokenize(struct llama_context * ctx, const std::string & text, bool add_bos);
|
|
|
|
//
|
|
// Console utils
|
|
//
|
|
|
|
#define ANSI_COLOR_RED "\x1b[31m"
|
|
#define ANSI_COLOR_GREEN "\x1b[32m"
|
|
#define ANSI_COLOR_YELLOW "\x1b[33m"
|
|
#define ANSI_COLOR_BLUE "\x1b[34m"
|
|
#define ANSI_COLOR_MAGENTA "\x1b[35m"
|
|
#define ANSI_COLOR_CYAN "\x1b[36m"
|
|
#define ANSI_COLOR_RESET "\x1b[0m"
|
|
#define ANSI_BOLD "\x1b[1m"
|
|
|
|
enum console_color_t {
|
|
CONSOLE_COLOR_DEFAULT=0,
|
|
CONSOLE_COLOR_PROMPT,
|
|
CONSOLE_COLOR_USER_INPUT
|
|
};
|
|
|
|
struct console_state {
|
|
bool use_color = false;
|
|
console_color_t color = CONSOLE_COLOR_DEFAULT;
|
|
};
|
|
|
|
void set_console_color(console_state & con_st, console_color_t color);
|
|
|
|
#if defined (_WIN32)
|
|
void win32_console_init(bool enable_color);
|
|
void win32_utf8_encode(const std::wstring & wstr, std::string & str);
|
|
#endif
|