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
examples/tokenize/tokenize.cpp
View file

@ -344,8 +344,10 @@ int main(int raw_argc, char ** raw_argv) {
return 1;
}
const llama_vocab * vocab = llama_model_get_vocab(model);
llama_context_params ctx_params = llama_context_default_params();
llama_context * ctx = llama_new_context_with_model(model, ctx_params);
llama_context * ctx = llama_init_from_model(model, ctx_params);
if (!ctx) {
fprintf(stderr, "Error: could not create context.\n");
return 1;
@ -365,7 +367,7 @@ int main(int raw_argc, char ** raw_argv) {
prompt = stdin_buffer.str();
}
const bool model_wants_add_bos = llama_add_bos_token(model);
const bool model_wants_add_bos = llama_vocab_get_add_bos(vocab);
const bool add_bos = model_wants_add_bos && !no_bos;
const bool parse_special = !no_parse_special;
const bool escape = !no_escape;
@ -375,7 +377,7 @@ int main(int raw_argc, char ** raw_argv) {
}
std::vector<llama_token> tokens;
tokens = common_tokenize(model, prompt, add_bos, parse_special);
tokens = common_tokenize(vocab, prompt, add_bos, parse_special);
if (printing_ids) {
printf("[");