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

llama : add llama_vocab, functions -> methods, naming (#11110)

Browse source 
* llama : functions -> methods (#11110)

* llama : add struct llama_vocab to the API (#11156)

ggml-ci

* hparams : move vocab params to llama_vocab (#11159)

ggml-ci

* vocab : more pimpl (#11165)

ggml-ci

* vocab : minor tokenization optimizations (#11160)

ggml-ci

Co-authored-by: Diego Devesa <slarengh@gmail.com>

* lora : update API names (#11167)

ggml-ci

* llama : update API names to use correct prefix (#11174)

* llama : update API names to use correct prefix

ggml-ci

* cont

ggml-ci

* cont

ggml-ci

* minor [no ci]

* vocab : llama_vocab_add_[be]os -> llama_vocab_get_add_[be]os (#11174)

ggml-ci

* vocab : llama_vocab_n_vocab -> llama_vocab_n_tokens (#11174)

ggml-ci

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2025-01-12 11:32:42 +02:00 • committed by GitHub
parent c05e8c9934
commit afa8a9ec9b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
68 changed files with 5855 additions and 5400 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/test-tokenizer-1-spm.cpp
View file

@ -43,7 +43,7 @@ int main(int argc, char ** argv) {
auto cparams = llama_context_default_params();
ctx = llama_new_context_with_model(model, cparams);
ctx = llama_init_from_model(model, cparams);
if (ctx == NULL) {
fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
@ -52,8 +52,10 @@ int main(int argc, char ** argv) {
}
}
const llama_vocab * vocab = llama_model_get_vocab(model);
//GGML_ASSERT(llama_vocab_type(model) == LLAMA_VOCAB_TYPE_SPM);
if (llama_vocab_type(model) != LLAMA_VOCAB_TYPE_SPM) {
if (llama_vocab_type(vocab) != LLAMA_VOCAB_TYPE_SPM) {
return 99;
}
@ -63,7 +65,7 @@ int main(int argc, char ** argv) {
atexit([]() { console::cleanup(); });
#endif
const int n_vocab = llama_n_vocab(model);
const int n_vocab = llama_vocab_n_tokens(vocab);
for (int i = 0; i < n_vocab; ++i) {
std::string str = common_detokenize(ctx, std::vector<int>(1, i), true);