mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 13:58:46 +01:00
edd4c14817
* tests : write a Python tokenizer test (wip) * llama : prefix input text for tokenization with whitespace * llama : distinguish pieces from decoded text + fix detokenization * common : add comments * examples : no longer manually add leading space when tokenizing * tests : use Python to generate tokenizer tests for C++ * tests : add option to tokenize text files ggml-ci * tests : add test-tokenizer-1.py * llama.cpp : fix LF token * hellaswag : move the concat space for clarity * tests : add falcon tests (py + cpp, currently do not pass Unicode) ggml-ci * common : temporary separate llama_detokenize calls for SPM and BPE --------- Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>
104 lines
2.9 KiB
C++
104 lines
2.9 KiB
C++
#include "common.h"
|
|
#include "llama.h"
|
|
#include "build-info.h"
|
|
|
|
#include <ctime>
|
|
|
|
#if defined(_MSC_VER)
|
|
#pragma warning(disable: 4244 4267) // possible loss of data
|
|
#endif
|
|
|
|
int main(int argc, char ** argv) {
|
|
gpt_params params;
|
|
|
|
if (gpt_params_parse(argc, argv, params) == false) {
|
|
return 1;
|
|
}
|
|
|
|
params.embedding = true;
|
|
|
|
if (params.n_ctx > 2048) {
|
|
fprintf(stderr, "%s: warning: model might not support context sizes greater than 2048 tokens (%d specified);"
|
|
"expect poor results\n", __func__, params.n_ctx);
|
|
}
|
|
|
|
fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
|
|
|
|
if (params.seed == LLAMA_DEFAULT_SEED) {
|
|
params.seed = time(NULL);
|
|
}
|
|
|
|
fprintf(stderr, "%s: seed = %u\n", __func__, params.seed);
|
|
|
|
std::mt19937 rng(params.seed);
|
|
if (params.random_prompt) {
|
|
params.prompt = gpt_random_prompt(rng);
|
|
}
|
|
|
|
llama_backend_init(params.numa);
|
|
|
|
llama_model * model;
|
|
llama_context * ctx;
|
|
|
|
// load the model
|
|
std::tie(model, ctx) = llama_init_from_gpt_params(params);
|
|
if (model == NULL) {
|
|
fprintf(stderr, "%s: error: unable to load model\n", __func__);
|
|
return 1;
|
|
}
|
|
|
|
// print system information
|
|
{
|
|
fprintf(stderr, "\n");
|
|
fprintf(stderr, "system_info: n_threads = %d / %d | %s\n",
|
|
params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info());
|
|
}
|
|
|
|
int n_past = 0;
|
|
|
|
// tokenize the prompt
|
|
auto embd_inp = ::llama_tokenize(ctx, params.prompt, true);
|
|
|
|
if (params.verbose_prompt) {
|
|
fprintf(stderr, "\n");
|
|
fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str());
|
|
fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size());
|
|
for (int i = 0; i < (int) embd_inp.size(); i++) {
|
|
fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_piece(ctx, embd_inp[i]).c_str());
|
|
}
|
|
fprintf(stderr, "\n");
|
|
}
|
|
|
|
if (embd_inp.size() > (size_t)params.n_ctx) {
|
|
fprintf(stderr, "%s: error: prompt is longer than the context window (%zu tokens, n_ctx = %d)\n",
|
|
__func__, embd_inp.size(), params.n_ctx);
|
|
return 1;
|
|
}
|
|
|
|
while (!embd_inp.empty()) {
|
|
int n_tokens = std::min(params.n_batch, (int) embd_inp.size());
|
|
if (llama_eval(ctx, embd_inp.data(), n_tokens, n_past, params.n_threads)) {
|
|
fprintf(stderr, "%s : failed to eval\n", __func__);
|
|
return 1;
|
|
}
|
|
n_past += n_tokens;
|
|
embd_inp.erase(embd_inp.begin(), embd_inp.begin() + n_tokens);
|
|
}
|
|
|
|
const int n_embd = llama_n_embd(ctx);
|
|
const auto embeddings = llama_get_embeddings(ctx);
|
|
|
|
for (int i = 0; i < n_embd; i++) {
|
|
printf("%f ", embeddings[i]);
|
|
}
|
|
printf("\n");
|
|
|
|
llama_print_timings(ctx);
|
|
llama_free(ctx);
|
|
llama_free_model(model);
|
|
|
|
llama_backend_free();
|
|
|
|
return 0;
|
|
}
|