mirror of
https://github.com/nomic-ai/gpt4all.git
synced 2024-09-11 21:27:37 +03:00
Signed-off-by: Adam Treat <treat.adam@gmail.com> Signed-off-by: Jared Van Bortel <jared@nomic.ai> Co-authored-by: Jared Van Bortel <jared@nomic.ai>
102 lines
2.6 KiB
C++
102 lines
2.6 KiB
C++
// Various helper functions and utilities
|
|
|
|
#pragma once
|
|
|
|
#include <algorithm>
|
|
#include <cstddef>
|
|
#include <cstdint>
|
|
#include <map>
|
|
#include <random>
|
|
#include <string>
|
|
#include <thread>
|
|
#include <vector>
|
|
|
|
//
|
|
// General purpose inline functions
|
|
//
|
|
constexpr inline unsigned long long operator ""_MiB(unsigned long long bytes)
|
|
{
|
|
return bytes*1024*1024;
|
|
}
|
|
|
|
//
|
|
// 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 = 200; // new tokens to predict
|
|
|
|
// sampling parameters
|
|
int32_t top_k = 40;
|
|
float top_p = 0.9f;
|
|
float temp = 0.9f;
|
|
|
|
int32_t n_batch = 8; // batch size for prompt processing
|
|
|
|
std::string model = "models/gpt-2-117M/ggml-model.bin"; // model path
|
|
std::string prompt;
|
|
};
|
|
|
|
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;
|
|
std::vector<std::string> special_tokens;
|
|
|
|
void add_special_token(const std::string &token) {
|
|
special_tokens.push_back(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);
|
|
|
|
// 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
|
|
//
|
|
// TODO: not sure if this implementation is correct
|
|
//
|
|
gpt_vocab::id gpt_sample_top_k_top_p(
|
|
const size_t actualVocabSize,
|
|
const int32_t * last_n_tokens_data,
|
|
int last_n_tokens_size,
|
|
const std::vector<float> logits,
|
|
int top_k,
|
|
double top_p,
|
|
double temp,
|
|
float repeat_penalty,
|
|
std::mt19937 & rng);
|