llama.cpp/utils.h
Stephan Walter 367946c668
Don't tell users to use a bad number of threads (#243)
The readme tells people to use the command line option "-t 8", causing 8
threads to be started. On systems with fewer than 8 cores, this causes a
significant slowdown. Remove the option from the example command lines
and use /proc/cpuinfo on Linux to determine a sensible default.
2023-03-17 19:47:35 +02:00

106 lines
3.1 KiB
C++

// Various helper functions and utilities
#pragma once
#include <string>
#include <map>
#include <vector>
#include <random>
#include <thread>
//
// CLI argument parsing
//
struct gpt_params {
int32_t seed = -1; // RNG seed
int32_t n_threads;
int32_t n_predict = 128; // new tokens to predict
int32_t repeat_last_n = 64; // last n tokens to penalize
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 = 1.30f;
int32_t n_batch = 8; // batch size for prompt processing
std::string model = "models/lamma-7B/ggml-model.bin"; // model path
std::string prompt;
bool use_color = false; // use color to distinguish generations and inputs
bool interactive = false; // interactive mode
bool interactive_start = false; // reverse prompt immediately
std::string antiprompt = ""; // string upon seeing which more user input is prompted
};
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
//
struct gpt_vocab {
using id = int32_t;
using token = std::string;
std::map<token, id> token_to_id;
std::map<id, token> id_to_token;
};
void replace(std::string & str, const std::string & needle, const std::string & replacement);
// poor-man's JSON parsing
std::map<std::string, int32_t> json_parse(const std::string & fname);
// split text into tokens
//
// ref: https://github.com/openai/gpt-2/blob/a74da5d99abaaba920de8131d64da2862a8f213b/src/encoder.py#L53
//
// Regex (Python):
// r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+"""
//
// Regex (C++):
// R"('s|'t|'re|'ve|'m|'ll|'d| ?[[:alpha:]]+| ?[[:digit:]]+| ?[^\s[:alpha:][:digit:]]+|\s+(?!\S)|\s+)"
//
std::vector<gpt_vocab::id> gpt_tokenize(const gpt_vocab & vocab, const std::string & text);
// TODO: this is probably wrong, but I cannot figure out how this tokenizer works ..
// ref: https://github.com/google/sentencepiece
std::vector<gpt_vocab::id> llama_tokenize(const gpt_vocab & vocab, const std::string & text, bool bos);
// load the tokens from encoder.json
bool gpt_vocab_init(const std::string & fname, gpt_vocab & vocab);
// sample next token given probabilities for each embedding
//
// - consider only the top K tokens
// - from them, consider only the top tokens with cumulative probability > P
//
gpt_vocab::id llama_sample_top_p_top_k(
const gpt_vocab & vocab,
const float * logits,
std::vector<gpt_vocab::id> & last_n_tokens,
double repeat_penalty,
int top_k,
double top_p,
double temp,
std::mt19937 & rng);
// filer to top K tokens from list of logits
void sample_top_k(std::vector<std::pair<double, gpt_vocab::id>> & logits_id, int top_k);
//
// Quantization
//
size_t ggml_quantize_q4_0(float * src, void * dst, int n, int k, int qk, int64_t * hist);
size_t ggml_quantize_q4_1(float * src, void * dst, int n, int k, int qk, int64_t * hist);