tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : more tokenizer fixes (#2810)

Browse Source 
* 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>
This commit is contained in:
Georgi Gerganov
2023-08-27 14:19:19 +03:00
committed by GitHub
parent 1591e2e590
commit edd4c14817
20 changed files with 671 additions and 224 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/CMakeLists.txt
View File

@ -25,8 +25,10 @@ endfunction()
llama_build_and_test_executable(test-quantize-fns.cpp)
llama_build_and_test_executable(test-quantize-perf.cpp)
llama_build_and_test_executable(test-sampling.cpp)
llama_build_executable(test-tokenizer-0.cpp)
llama_test_executable (test-tokenizer-0.llama test-tokenizer-0.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama.gguf)
llama_build_executable(test-tokenizer-0-llama.cpp)
llama_test_executable (test-tokenizer-0-llama test-tokenizer-0-llama.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama.gguf)
llama_build_executable(test-tokenizer-0-falcon.cpp)
#llama_test_executable (test-tokenizer-0-falcon test-tokenizer-0-falcon.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
llama_build_executable(test-tokenizer-1.cpp)
# test-tokenizer-1 requires a BPE vocab. re-enable when we have one.
#llama_test_executable (test-tokenizer-1.llama test-tokenizer-1.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)

178
tests/test-tokenizer-0-falcon.cpp Normal file
View File

@ -0,0 +1,178 @@
#include "llama.h"
#include "common.h"
#include <cstdio>
#include <string>
#include <map>
#include <vector>
#include <fstream>
// generate using test-tokenizer-0-falcon.py
static const std::map<std::string, std::vector<llama_token>> & k_tests() {
static std::map<std::string, std::vector<llama_token>> _k_tests = {
{ "" , { }, },
{ " " , { 204, }, },
{ " " , { 258, }, },
{ " " , { 466, }, },
{ "\t" , { 192, }, },
{ "\n" , { 193, }, },
{ "\t\n" , { 19125, }, },
{ "Hello world" , { 9856, 1079, }, },
{ " Hello world" , { 23090, 1079, }, },
{ "Hello World" , { 9856, 2889, }, },
{ " Hello World" , { 23090, 2889, }, },
{ " Hello World!" , { 23090, 2889, 12, }, },
{ "Hello, world!" , { 9856, 23, 1079, 12, }, },
{ " Hello, world!" , { 23090, 23, 1079, 12, }, },
{ " this is 🦙.cpp" , { 414, 304, 3346, 111, 231, 25, 29247, }, },
{ "w048 7tuijk dsdfhu" , { 98, 55866, 204, 34, 16682, 7149, 36190, 6869, 11481, }, },
{ "нещо на Български" , { 150, 133, 6207, 151, 215, 150, 134, 5052, 133, 6279, 5052, 223, 151, 216, 49679, 123, 53110, 47043, 7795, }, },
{ "កាន់តែពិសេសអាចខលចេញ" , { 38154, 206, 38154, 126, 38154, 225, 167, 237, 217, 38154, 221, 167, 237, 208, 38154, 228, 38154, 127, 38154, 237, 167, 237, 207, 38154, 237, 38154, 107, 38154, 126, 38154, 211, 38154, 207, 38154, 233, 38154, 211, 167, 237, 207, 38154, 215, }, },
{ "🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)", { 2571, 232, 206, 204, 19, 11003, 20, 8196, 126, 283, 219, 48778, 116, 13392, 204, 19, 51831, 732, 63209, 1741, 7955, 522, 20, 22438, 211, 204, 19, 7927, 53360, 325, 504, 701, 946, 10930, 20, }, },
{ "Hello" , { 9856, }, },
{ " Hello" , { 23090, }, },
{ " Hello" , { 204, 23090, }, },
{ " Hello" , { 258, 23090, }, },
{ " Hello" , { 466, 23090, }, },
{ " Hello\n Hello" , { 466, 23090, 742, 23090, }, },
};
return _k_tests;
}
int main(int argc, char **argv) {
if (argc < 2) {
fprintf(stderr, "Usage: %s vocab-file [text-file]\n", argv[0]);
return 1;
}
const std::string fname = argv[1];
std::string fname_text;
if (argc > 2) {
fname_text = argv[2];
}
fprintf(stderr, "%s : reading vocab from: '%s'\n", __func__, fname.c_str());
llama_model * model;
llama_context * ctx;
llama_backend_init(false);
// load the vocab
{
auto lparams = llama_context_default_params();
lparams.vocab_only = true;
model = llama_load_model_from_file(fname.c_str(), lparams);
if (model == NULL) {
fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
return 1;
}
ctx = llama_new_context_with_model(model, lparams);
if (ctx == NULL) {
fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
llama_free_model(model);
return 1;
}
}
if (llama_vocab_type(ctx) != LLAMA_VOCAB_TYPE_BPE) {
fprintf(stderr, "%s : error: vocab type is not SPM\n", __func__);
llama_free_model(model);
llama_free(ctx);
return 2;
}
bool success = true;
for (const auto & test_kv : k_tests()) {
const std::vector<llama_token> res = llama_tokenize(ctx, test_kv.first, false);
printf("\n");
printf("src: '%s'\n", test_kv.first.c_str());
printf("res: '%s'\n", llama_detokenize_bpe(ctx, res).c_str());
printf("tok: ");
for (const auto & tok : res) {
printf("%d ", tok);
}
printf("\n");
bool correct = res.size() == test_kv.second.size();
for (int i = 0; i < (int) res.size() && correct; ++i) {
if (test_kv.second[i] != res[i]) {
correct = false;
}
}
if (!correct) {
fprintf(stderr, "%s : failed test: '%s'\n", __func__, test_kv.first.c_str());
fprintf(stderr, "%s : detokenized to: '%s' instead of '%s'\n", __func__,
llama_detokenize_bpe(ctx, res).c_str(),
llama_detokenize_bpe(ctx, test_kv.second).c_str());
fprintf(stderr, "%s : expected tokens: ", __func__);
for (const auto & t : test_kv.second) {
fprintf(stderr, "%6d, ", t);
}
fprintf(stderr, "\n");
fprintf(stderr, "%s : got tokens: ", __func__);
for (const auto & t : res) {
fprintf(stderr, "%6d, ", t);
}
fprintf(stderr, "\n");
success = false;
}
}
if (!fname_text.empty()) {
fprintf(stderr, "%s : tokenizing: '%s'\n", __func__, fname_text.c_str());
std::string text;
{
std::ifstream ifs(fname_text);
if (!ifs) {
fprintf(stderr, "%s : error: could not open file '%s'\n", __func__, fname_text.c_str());
return 1;
}
text = std::string(std::istreambuf_iterator<char>(ifs), std::istreambuf_iterator<char>());
}
fprintf(stderr, "%s : text size: %zu\n", __func__, text.size());
const std::vector<llama_token> res = llama_tokenize(ctx, text, true);
fprintf(stderr, "%s : tokens: %zu\n", __func__, res.size());
{
const std::string fname_out = fname_text + ".tokcpp";
std::ofstream ofs(fname_out);
if (!ofs) {
fprintf(stderr, "%s : error: could not open file '%s'\n", __func__, fname_out.c_str());
return 1;
}
for (const auto & tok : res) {
ofs << tok << " ";
}
ofs << "\n";
}
fprintf(stderr, "%s : tokens written to '%s'\n", __func__, (fname_text + ".tokcpp").c_str());
}
llama_free_model(model);
llama_free(ctx);
llama_backend_free();
return success ? 0 : 3;
}

83
tests/test-tokenizer-0-falcon.py Normal file
View File

@ -0,0 +1,83 @@
# tests with BPE tokenizer
import os
import sys
import argparse
from transformers import AutoTokenizer
parser = argparse.ArgumentParser()
parser.add_argument("dir_tokenizer", help="directory containing 'tokenizer.model' file")
parser.add_argument("--fname-tok", help="path to a text file to tokenize")
args = parser.parse_args()
dir_tokenizer = args.dir_tokenizer
tokenizer = AutoTokenizer.from_pretrained(dir_tokenizer)
tests = [
"",
" ",
" ",
" ",
"\t",
"\n",
"\t\n",
"Hello world",
" Hello world",
"Hello World",
" Hello World",
" Hello World!",
"Hello, world!",
" Hello, world!",
" this is 🦙.cpp",
"w048 7tuijk dsdfhu",
"нещо на Български",
"កាន់តែពិសេសអាចខលចេញ",
"🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)",
"Hello",
" Hello",
" Hello",
" Hello",
" Hello",
" Hello\n Hello",
]
for text in tests:
print('text: ', text)
print(tokenizer.encode(text))
print(tokenizer.decode(tokenizer.encode(text)))
print("\n\ntests for C++:\n")
for text in tests:
res = tokenizer.encode(text)
k = text.replace('\n', '\\n')
k = k.replace('\t', '\\t')
k = '"' + k + '"'
print("{ %-24s, { " % k, end='')
for x in res:
print("%7d," % x, end='')
print(" }, },")
print(tokenizer.encode('hello'))
print(tokenizer.encode('world'))
print(tokenizer.encode(' world'))
print(tokenizer.encode('hello world'))
fname_tok = args.fname_tok
if fname_tok:
print('tokenizing file: ', fname_tok)
fname_out = fname_tok + '.tok'
with open(fname_tok, 'r') as f:
lines = f.readlines()
s = ''.join(lines)
res = tokenizer.encode(s)
# write to file
with open(fname_out, 'w') as f:
for x in res:
f.write(str(x) + ' ')
f.write('\n')
print('len(res): ', len(res))
print('len(lines): ', len(lines))
print('results written to: ', fname_out)

182
tests/test-tokenizer-0-llama.cpp Normal file
View File

@ -0,0 +1,182 @@
#include "llama.h"
#include "common.h"
#include <cstdio>
#include <string>
#include <map>
#include <vector>
#include <fstream>
// generate using test-tokenizer-0-llama.py
static const std::map<std::string, std::vector<llama_token>> & k_tests() {
static std::map<std::string, std::vector<llama_token>> _k_tests = {
{ "" , { }, },
{ " " , { 259, }, },
{ " " , { 1678, }, },
{ " " , { 268, }, },
{ "\t" , { 29871, 12, }, },
{ "\n" , { 29871, 13, }, },
{ "\t\n" , { 29871, 12, 13, }, },
{ "Hello world" , { 15043, 3186, }, },
{ " Hello world" , { 29871, 15043, 3186, }, },
{ "Hello World" , { 15043, 2787, }, },
{ " Hello World" , { 29871, 15043, 2787, }, },
{ " Hello World!" , { 29871, 15043, 2787, 29991, }, },
{ "Hello, world!" , { 15043, 29892, 3186, 29991, }, },
{ " Hello, world!" , { 29871, 15043, 29892, 3186, 29991, }, },
{ " this is 🦙.cpp" , { 29871, 445, 338, 29871, 243, 162, 169, 156, 29889, 8223, }, },
{ "w048 7tuijk dsdfhu" , { 281, 29900, 29946, 29947, 29871, 29955, 9161, 13535, 18031, 2176, 6905, }, },
{ "нещо на Български" , { 1538, 4851, 665, 1386, 29713, 1305, }, },
{ "កាន់តែពិសេសអាចខលចេញ" , { 29871, 31849, 31324, 31934, 228, 162, 142, 228, 161, 146, 228, 162, 133, 228, 161, 153, 228, 161, 186, 31708, 228, 162, 132, 31708, 228, 161, 165, 31324, 228, 161, 136, 228, 161, 132, 228, 161, 158, 228, 161, 136, 228, 162, 132, 228, 161, 140, }, },
{ "🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)", { 29871, 243, 162, 157, 131, 313, 8945, 29897, 29871, 243, 162, 155, 185, 30722, 243, 162, 143, 174, 30598, 313, 20787, 953, 3848, 275, 16125, 630, 29897, 29871, 31681, 313, 6194, 953, 29877, 2397, 393, 756, 967, 1914, 5993, 29897, }, },
{ "Hello" , { 15043, }, },
{ " Hello" , { 29871, 15043, }, },
{ " Hello" , { 259, 15043, }, },
{ " Hello" , { 1678, 15043, }, },
{ " Hello" , { 268, 15043, }, },
{ " Hello\n Hello" , { 268, 15043, 13, 1678, 15043, }, },
};
return _k_tests;
}
int main(int argc, char **argv) {
if (argc < 2) {
fprintf(stderr, "Usage: %s vocab-file [text-file]\n", argv[0]);
return 1;
}
const std::string fname = argv[1];
std::string fname_text;
if (argc > 2) {
fname_text = argv[2];
}
fprintf(stderr, "%s : reading vocab from: '%s'\n", __func__, fname.c_str());
llama_model * model;
llama_context * ctx;
llama_backend_init(false);
// load the vocab
{
auto lparams = llama_context_default_params();
lparams.vocab_only = true;
model = llama_load_model_from_file(fname.c_str(), lparams);
if (model == NULL) {
fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
return 1;
}
ctx = llama_new_context_with_model(model, lparams);
if (ctx == NULL) {
fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
llama_free_model(model);
return 1;
}
}
if (llama_vocab_type(ctx) != LLAMA_VOCAB_TYPE_SPM) {
fprintf(stderr, "%s : error: vocab type is not SPM\n", __func__);
llama_free_model(model);
llama_free(ctx);
return 2;
}
bool success = true;
for (const auto & test_kv : k_tests()) {
const std::vector<llama_token> res_bos = llama_tokenize(ctx, test_kv.first, true);
const std::vector<llama_token> res_nobos = llama_tokenize(ctx, test_kv.first, false);
printf("\n");
printf("src: '%s'\n", test_kv.first.c_str());
printf("res: '%s'\n", llama_detokenize_spm(ctx, res_bos).c_str());
printf("tok: ");
for (const auto & tok : res_bos) {
printf("%d ", tok);
}
printf("\n");
bool correct = res_nobos.size() == test_kv.second.size() && res_bos.size() == res_nobos.size() + 1 && res_bos[0] == 1;
for (int i = 0; i < (int) res_nobos.size() && correct; ++i) {
if (test_kv.second[i] != res_bos[i + 1]) {
correct = false;
}
if (test_kv.second[i] != res_nobos[i]) {
correct = false;
}
}
if (!correct) {
fprintf(stderr, "%s : failed test: '%s'\n", __func__, test_kv.first.c_str());
fprintf(stderr, "%s : detokenized to: '%s' instead of '%s'\n", __func__,
llama_detokenize_spm(ctx, res_nobos).c_str(),
llama_detokenize_spm(ctx, test_kv.second).c_str());
fprintf(stderr, "%s : expected tokens: ", __func__);
for (const auto & t : test_kv.second) {
fprintf(stderr, "%6d, ", t);
}
fprintf(stderr, "\n");
fprintf(stderr, "%s : got tokens: ", __func__);
for (const auto & t : res_nobos) {
fprintf(stderr, "%6d, ", t);
}
fprintf(stderr, "\n");
success = false;
}
}
if (!fname_text.empty()) {
fprintf(stderr, "%s : tokenizing: '%s'\n", __func__, fname_text.c_str());
std::string text;
{
std::ifstream ifs(fname_text);
if (!ifs) {
fprintf(stderr, "%s : error: could not open file '%s'\n", __func__, fname_text.c_str());
return 1;
}
text = std::string(std::istreambuf_iterator<char>(ifs), std::istreambuf_iterator<char>());
}
fprintf(stderr, "%s : text size: %zu\n", __func__, text.size());
const std::vector<llama_token> res = llama_tokenize(ctx, text, true);
fprintf(stderr, "%s : tokens: %zu\n", __func__, res.size());
{
const std::string fname_out = fname_text + ".tokcpp";
std::ofstream ofs(fname_out);
if (!ofs) {
fprintf(stderr, "%s : error: could not open file '%s'\n", __func__, fname_out.c_str());
return 1;
}
for (const auto & tok : res) {
ofs << tok << " ";
}
ofs << "\n";
}
fprintf(stderr, "%s : tokens written to '%s'\n", __func__, (fname_text + ".tokcpp").c_str());
}
llama_free_model(model);
llama_free(ctx);
llama_backend_free();
return success ? 0 : 3;
}

95
tests/test-tokenizer-0-llama.py Normal file
View File

@ -0,0 +1,95 @@
# tests with SPM tokenizer
import os
import sys
import argparse
from sentencepiece import SentencePieceProcessor
parser = argparse.ArgumentParser()
parser.add_argument("dir_tokenizer", help="directory containing 'tokenizer.model' file")
parser.add_argument("--fname-tok", help="path to a text file to tokenize")
args = parser.parse_args()
dir_tokenizer = args.dir_tokenizer
tokenizer = SentencePieceProcessor(dir_tokenizer + '/tokenizer.model')
tests = [
"",
" ",
" ",
" ",
"\t",
"\n",
"\t\n",
"Hello world",
" Hello world",
"Hello World",
" Hello World",
" Hello World!",
"Hello, world!",
" Hello, world!",
" this is 🦙.cpp",
"w048 7tuijk dsdfhu",
"нещо на Български",
"កាន់តែពិសេសអាចខលចេញ",
"🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)",
"Hello",
" Hello",
" Hello",
" Hello",
" Hello",
" Hello\n Hello",
]
for text in tests:
print('text: ', text)
print('\nwith bos:')
print(tokenizer.encode(text, add_bos=True))
print(tokenizer.decode(tokenizer.encode(text, add_bos=True)))
print('\nwithout bos:')
print(tokenizer.encode(text, add_bos=False))
print(tokenizer.decode(tokenizer.encode(text, add_bos=False)))
print("'" + tokenizer.id_to_piece(15043) + "'") # '_Hello'
print("'" + tokenizer.id_to_piece(29871) + "'") # '_'
print("'" + tokenizer.decode([15043]) + "'") # 'Hello'
print("'" + tokenizer.decode([15043, 15043]) + "'") # 'Hello Hello'
print("'" + tokenizer.decode([29871, 15043]) + "'") # ' Hello'
print("'" + tokenizer.decode([29871, 15043, 29871, 15043]) + "'") # ' Hello Hello'
print("\n\ntests for C++:\n")
for text in tests:
res = tokenizer.encode(text, add_bos=False)
k = text.replace('\n', '\\n')
k = k.replace('\t', '\\t')
k = '"' + k + '"'
print("{ %-24s, { " % k, end='')
for x in res:
print("%7d," % x, end='')
print(" }, },")
print(tokenizer.encode('hello'))
print(tokenizer.encode('world'))
print(tokenizer.encode(' world'))
print(tokenizer.encode('hello world'))
fname_tok = args.fname_tok
if fname_tok:
print('tokenizing file: ', fname_tok)
fname_out = fname_tok + '.tok'
with open(fname_tok, 'r') as f:
lines = f.readlines()
s = ''.join(lines)
res = tokenizer.encode(s, add_bos=True)
# write to file
with open(fname_out, 'w') as f:
for x in res:
f.write(str(x) + ' ')
f.write('\n')
print('len(res): ', len(res))
print('len(lines): ', len(lines))
print('results written to: ', fname_out)

141
tests/test-tokenizer-0.cpp
View File

@ -1,141 +0,0 @@
#include "llama.h"
#include "common.h"
#include <cstdio>
#include <string>
#include <map>
#include <vector>
static std::string unescape_whitespace(llama_context* ctx, const std::vector<llama_token>& tokens) {
std::string result;
for (size_t i = 0; i < tokens.size(); ++i) {
result += llama_token_to_str(ctx, tokens[i]);
}
return result;
}
static const std::map<std::string, std::vector<llama_token>> & k_tests() {
static std::map<std::string, std::vector<llama_token>> _k_tests = {
{ " ", {1, 259, }, },
{ " ", { 1, 1678, }, },
{ " ", { 1, 268, }, },
{ "\t", { 1, 29871, 12, }, },
{ "\n", { 1, 29871, 13, }, },
{ "\t\n", { 1, 29871, 12, 13, }, },
{ "Hello world", { 1, 15043, 3186, }, },
{ " Hello world", { 1, 29871, 15043, 3186, }, },
{ "Hello World", { 1, 15043, 2787, }, },
{ " Hello World", { 1, 29871, 15043, 2787, }, },
{ " Hello World!", { 1, 29871, 15043, 2787, 29991, }, },
{ " this is 🦙.cpp", { 1, 29871, 445, 338, 29871, 243, 162, 169, 156, 29889, 8223, }, },
{ "w048 7tuijk dsdfhu", { 1, 281, 29900, 29946, 29947, 29871, 29955, 9161, 13535, 18031, 2176, 6905, }, },
{ "нещо на Български", { 1, 1538, 4851, 665, 1386, 29713, 1305, }, },
{ "កាន់តែពិសេសអាចខលចេញ", { 1, 29871, 31849, 31324, 31934, 228, 162, 142, 228, 161,
146, 228, 162, 133, 228, 161, 153, 228, 161, 186,
31708, 228, 162, 132, 31708, 228, 161, 165, 31324, 228,
161, 136, 228, 161, 132, 228, 161, 158, 228, 161,
136, 228, 162, 132, 228, 161, 140, }, },
{ "🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)",
{ 1, 29871, 243, 162, 157, 131, 313, 8945, 29897, 29871,
243, 162, 155, 185, 30722, 243, 162, 143, 174, 30598,
313, 20787, 953, 3848, 275, 16125, 630, 29897, 29871, 31681,
313, 6194, 953, 29877, 2397, 393, 756, 967, 1914, 5993, 29897, }, },
{ "Hello", { 1, 15043 }, },
{ " Hello", { 1, 29871, 15043 }, },
{ " Hello", { 1, 259, 15043 }, },
{ " Hello", { 1, 1678, 15043 }, },
{ " Hello", { 1, 268, 15043 }, },
{ " Hello\n Hello", { 1, 268, 15043, 13, 1678, 15043 }, },
};
return _k_tests;
}
int main(int argc, char **argv) {
if (argc < 2) {
fprintf(stderr, "Usage: %s <vocab-file>\n", argv[0]);
return 1;
}
const std::string fname = argv[1];
fprintf(stderr, "%s : reading vocab from: '%s'\n", __func__, fname.c_str());
llama_model * model;
llama_context * ctx;
llama_backend_init(false);
// load the vocab
{
auto lparams = llama_context_default_params();
lparams.vocab_only = true;
model = llama_load_model_from_file(fname.c_str(), lparams);
if (model == NULL) {
fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
return 1;
}
ctx = llama_new_context_with_model(model, lparams);
if (ctx == NULL) {
fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
llama_free_model(model);
return 1;
}
}
const int n_vocab = llama_n_vocab(ctx);
if (n_vocab != 32000) {
fprintf(stderr, "%s : expected 32000 tokens, got %d\n", __func__, n_vocab);
llama_free_model(model);
llama_free(ctx);
return 2;
}
bool success = true;
for (const auto & test_kv : k_tests()) {
// Add a space in front of the first character to match OG llama tokenizer behavior
std::vector<llama_token> res = llama_tokenize(ctx, " " + test_kv.first, true);
fprintf(stderr, "%s : '%s' tokenized to '%s'\n",
__func__, test_kv.first.c_str(), unescape_whitespace(ctx, res).c_str());
bool correct = res.size() == test_kv.second.size();
for (int i = 0; i < (int) res.size() && correct; ++i) {
if (res[i] != test_kv.second[i]) {
correct = false;
}
}
if (!correct) {
fprintf(stderr, "%s : failed test: '%s'\n", __func__, test_kv.first.c_str());
fprintf(stderr, "%s : detokenized to: '%s' instead of '%s'\n", __func__,
unescape_whitespace(ctx, res).c_str(), unescape_whitespace(ctx, test_kv.second).c_str());
fprintf(stderr, "%s : expected tokens: ", __func__);
for (const auto & t : test_kv.second) {
fprintf(stderr, "%6d, ", t);
}
fprintf(stderr, "\n");
fprintf(stderr, "%s : got tokens: ", __func__);
for (const auto & t : res) {
fprintf(stderr, "%6d, ", t);
}
fprintf(stderr, "\n");
success = false;
}
}
llama_free_model(model);
llama_free(ctx);
llama_backend_free();
return success ? 0 : 3;
}

14
tests/test-tokenizer-1.cpp
View File

@ -22,14 +22,6 @@ static std::string escape_whitespace(const std::string& text) {
return result;
}
static std::string unescape_whitespace(llama_context * ctx, const std::vector<llama_token> & tokens) {
std::string result;
for (size_t i = 0; i < tokens.size(); ++i) {
result += llama_token_to_str(ctx, tokens[i]);
}
return result;
}
int main(int argc, char **argv) {
if (argc < 2) {
fprintf(stderr, "Usage: %s <vocab-file>\n", argv[0]);
@ -72,13 +64,13 @@ int main(int argc, char **argv) {
const int n_vocab = llama_n_vocab(ctx);
for (int i = 0; i < n_vocab; ++i) {
std::string forward = llama_token_to_str(ctx, i);
std::string forward = llama_token_to_piece(ctx, i);
std::vector<llama_token> tokens = llama_tokenize(ctx, forward, false);
if (tokens.size() == 1) {
if (i != tokens[0]) {
std::string backward = llama_token_to_str(ctx, tokens[0]);
std::string backward = llama_token_to_piece(ctx, tokens[0]);
fprintf(stderr, "%s : error: token %d is string %s but bpe returns token %d %s\n",
__func__, i, llama_token_to_str(ctx, i).c_str(), tokens[0], backward.c_str());
__func__, i, llama_token_to_piece(ctx, i).c_str(), tokens[0], backward.c_str());
return 2;
}
}