refactor: reorganize the vocab file structure (#1271)

This commit is contained in:
leejet
2026-02-11 00:44:17 +08:00
committed by GitHub
parent adea272225
commit 636d3cb6ff
14 changed files with 67 additions and 55 deletions

View File

@@ -16,10 +16,6 @@
#include "model.h"
#include "stable-diffusion.h"
#include "util.h"
#include "vocab.hpp"
#include "vocab_mistral.hpp"
#include "vocab_qwen.hpp"
#include "vocab_umt5.hpp"
#include "ggml-alloc.h"
#include "ggml-backend.h"
@@ -1340,36 +1336,6 @@ void ModelLoader::set_wtype_override(ggml_type wtype, std::string tensor_type_ru
}
}
std::string ModelLoader::load_merges() {
std::string merges_utf8_str(reinterpret_cast<const char*>(merges_utf8_c_str), sizeof(merges_utf8_c_str));
return merges_utf8_str;
}
std::string ModelLoader::load_qwen2_merges() {
std::string merges_utf8_str(reinterpret_cast<const char*>(qwen2_merges_utf8_c_str), sizeof(qwen2_merges_utf8_c_str));
return merges_utf8_str;
}
std::string ModelLoader::load_mistral_merges() {
std::string merges_utf8_str(reinterpret_cast<const char*>(mistral_merges_utf8_c_str), sizeof(mistral_merges_utf8_c_str));
return merges_utf8_str;
}
std::string ModelLoader::load_mistral_vocab_json() {
std::string json_str(reinterpret_cast<const char*>(mistral_vocab_json_utf8_c_str), sizeof(mistral_vocab_json_utf8_c_str));
return json_str;
}
std::string ModelLoader::load_t5_tokenizer_json() {
std::string json_str(reinterpret_cast<const char*>(t5_tokenizer_json_str), sizeof(t5_tokenizer_json_str));
return json_str;
}
std::string ModelLoader::load_umt5_tokenizer_json() {
std::string json_str(reinterpret_cast<const char*>(umt5_tokenizer_json_str), sizeof(umt5_tokenizer_json_str));
return json_str;
}
bool ModelLoader::load_tensors(on_new_tensor_cb_t on_new_tensor_cb, int n_threads_p, bool enable_mmap) {
int64_t process_time_ms = 0;
std::atomic<int64_t> read_time_ms(0);