DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 03:24:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: move parameter and tokenizer diagnostics to debug (#2135)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-10-13 23:37:58 +08:00
1 parent 46362fc4c0
commit 1d0a58a350
8 files changed
+14 -14
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/tokenizers/clip_tokenizer.cpp
+1 -1
View File
@@ -63,7 +63,7 @@ void CLIPTokenizer::load_from_merges(const std::string& merges_utf8_str) {
}
vocab.push_back(utf8_to_utf32("<|startoftext|>"));
vocab.push_back(utf8_to_utf32("<|endoftext|>"));
LOG_VERBOSE("vocab size: %zu", vocab.size());
LOG_DEBUG("vocab size: %zu", vocab.size());
int i = 0;
for (const auto& token : vocab) {
encoder[token] = i;
src/tokenizers/gemma_tokenizer.cpp
+2 -2
View File
@@ -29,7 +29,7 @@ void GemmaTokenizer::load_from_merges(const std::string& merges_utf8_str, const
decoder[i] = token;
}
encoder_len = static_cast<int>(vocab.size());
LOG_VERBOSE("vocab size: %d", encoder_len);
LOG_DEBUG("vocab size: %d", encoder_len);
std::vector<std::u32string> merges = split_utf32(merges_utf8_str);
std::vector<std::pair<std::u32string, std::u32string>> merge_pairs;
@@ -37,7 +37,7 @@ void GemmaTokenizer::load_from_merges(const std::string& merges_utf8_str, const
size_t space_pos = merge.find(' ');
merge_pairs.emplace_back(merge.substr(0, space_pos), merge.substr(space_pos + 1));
}
LOG_VERBOSE("merges size %zu", merge_pairs.size());
LOG_DEBUG("merges size %zu", merge_pairs.size());
int rank = 0;
for (const auto& merge : merge_pairs) {
src/tokenizers/mistral_tokenizer.cpp
+2 -2
View File
@@ -20,7 +20,7 @@ void MistralTokenizer::load_from_merges(const std::string& merges_utf8_str, cons
decoder[i] = token;
}
encoder_len = static_cast<int>(vocab.size());
LOG_VERBOSE("vocab size: %d", encoder_len);
LOG_DEBUG("vocab size: %d", encoder_len);
auto byte_unicode_pairs = bytes_to_unicode();
byte_encoder = std::map<int, std::u32string>(byte_unicode_pairs.begin(), byte_unicode_pairs.end());
@@ -28,7 +28,7 @@ void MistralTokenizer::load_from_merges(const std::string& merges_utf8_str, cons
byte_decoder[pair.second] = pair.first;
}
std::vector<std::u32string> merges = split_utf32(merges_utf8_str);
LOG_VERBOSE("merges size %zu", merges.size());
LOG_DEBUG("merges size %zu", merges.size());
std::vector<std::pair<std::u32string, std::u32string>> merge_pairs;
for (const auto& merge : merges) {
size_t space_pos = merge.find(' ');
src/tokenizers/qwen2_tokenizer.cpp
+2 -2
View File
@@ -11,7 +11,7 @@ void Qwen2Tokenizer::load_from_merges(const std::string& merges_utf8_str) {
}
std::vector<std::u32string> merges = split_utf32(merges_utf8_str);
LOG_VERBOSE("merges size %zu", merges.size());
LOG_DEBUG("merges size %zu", merges.size());
std::vector<std::pair<std::u32string, std::u32string>> merge_pairs;
for (const auto& merge : merges) {
size_t space_pos = merge.find(' ');
@@ -36,7 +36,7 @@ void Qwen2Tokenizer::load_from_merges(const std::string& merges_utf8_str) {
i++;
}
encoder_len = i;
LOG_VERBOSE("vocab size: %d", encoder_len);
LOG_DEBUG("vocab size: %d", encoder_len);
int rank = 0;
for (const auto& merge : merge_pairs) {