vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : tokenizer fixes (#2549)

Browse source 
* Merge tokenizer fixes into the gguf branch.

* Add test vocabularies
This commit is contained in:
goerch 2023-08-14 18:30:28 +02:00 • committed by GitHub
parent 8af3a99ff1
commit ec1b100720
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
17 changed files with 612 additions and 147 deletions
Download patch file Download diff file Expand all files Collapse all files

45
tests/test-tokenizer-0.cpp
View file

@ -1,3 +1,4 @@
#define LLAMA_API_CPP // TODO: eliminate me
#include "llama.h"
#include <cstdio>
@ -5,16 +6,40 @@
#include <map>
#include <vector>
static std::string unescape_whitespace(llama_context* ctx, const std::vector<llama_token>& tokens) {
std::string result;
for (int 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 = {
{ "Hello World", { 1, 10994, 2787, }, },
{ " Hello World", { 1, 15043, 2787, }, },
{ " Hello World!", { 1, 15043, 2787, 29991, }, },
{ " this is 🦙.cpp", { 1, 445, 338, 29871, 243, 162, 169, 156, 29889, 8223, }, },
{ "w048 7tuijk dsdfhu", { 1, 29893, 29900, 29946, 29947, 29871, 29955, 9161, 13535, 18031, 2176, 6905, }, },
{ "нещо на Български", { 1, 821, 4851, 665, 1386, 29713, 1305, }, },
};
{ " ", {1, 259, }, },
{ "\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, }, },
};
return _k_tests;
};
@ -65,9 +90,9 @@ int main(int argc, char **argv) {
}
for (const auto & test_kv : k_tests()) {
std::vector<llama_token> res(test_kv.first.size());
const int n = llama_tokenize(ctx, test_kv.first.c_str(), res.data(), int(res.size()), true);
res.resize(n);
std::vector<llama_token> res = llama_tokenize(ctx, test_kv.first.c_str(), 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();