mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-27 06:39:25 +01:00
3a0dcb3920
This new mode works by first loading the model then listening for TCP connections on a port. When a connection is received, arguments will be parsed using a simple protocol: - First the number of arguments will be read followed by a newline character. - Then each argument will be read, separated by the 0 byte. - With this we build an argument vector, similar to what is passed to the program entry point. We pass this to gpt_params_parse. Finally `run` will be executed with the input/output streams connected to the socket. Signed-off-by: Thiago Padilha <thiago@padilha.cc>
62 lines
2.0 KiB
C++
62 lines
2.0 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
|
|
|
|
// sampling parameters
|
|
int32_t top_k = 40;
|
|
float top_p = 0.95f;
|
|
float temp = 0.80f;
|
|
float repeat_penalty = 1.10f;
|
|
|
|
int32_t n_batch = 8; // batch size for prompt processing
|
|
|
|
std::string model = "models/lamma-7B/ggml-model.bin"; // model path
|
|
std::string prompt = "";
|
|
|
|
std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
|
|
|
|
bool memory_f16 = false; // 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 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
|
|
|
|
#ifndef _WIN32
|
|
std::string listen_port = ""; // TCP port for when running in server mode
|
|
#endif
|
|
};
|
|
|
|
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);
|