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

13
examples/simple/simple.cpp
View file

@ -84,6 +84,7 @@ int main(int argc, char ** argv) {
model_params.n_gpu_layers = ngl;
llama_model * model = llama_model_load_from_file(model_path.c_str(), model_params);
const llama_vocab * vocab = llama_model_get_vocab(model);
if (model == NULL) {
fprintf(stderr , "%s: error: unable to load model\n" , __func__);
@ -93,11 +94,11 @@ int main(int argc, char ** argv) {
// tokenize the prompt
// find the number of tokens in the prompt
const int n_prompt = -llama_tokenize(model, prompt.c_str(), prompt.size(), NULL, 0, true, true);
const int n_prompt = -llama_tokenize(vocab, prompt.c_str(), prompt.size(), NULL, 0, true, true);
// allocate space for the tokens and tokenize the prompt
std::vector<llama_token> prompt_tokens(n_prompt);
if (llama_tokenize(model, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), true, true) < 0) {
if (llama_tokenize(vocab, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), true, true) < 0) {
fprintf(stderr, "%s: error: failed to tokenize the prompt\n", __func__);
return 1;
}
@ -112,7 +113,7 @@ int main(int argc, char ** argv) {
// enable performance counters
ctx_params.no_perf = false;
llama_context * ctx = llama_new_context_with_model(model, ctx_params);
llama_context * ctx = llama_init_from_model(model, ctx_params);
if (ctx == NULL) {
fprintf(stderr , "%s: error: failed to create the llama_context\n" , __func__);
@ -131,7 +132,7 @@ int main(int argc, char ** argv) {
for (auto id : prompt_tokens) {
char buf[128];
int n = llama_token_to_piece(model, id, buf, sizeof(buf), 0, true);
int n = llama_token_to_piece(vocab, id, buf, sizeof(buf), 0, true);
if (n < 0) {
fprintf(stderr, "%s: error: failed to convert token to piece\n", __func__);
return 1;
@ -164,12 +165,12 @@ int main(int argc, char ** argv) {
new_token_id = llama_sampler_sample(smpl, ctx, -1);
// is it an end of generation?
if (llama_token_is_eog(model, new_token_id)) {
if (llama_vocab_is_eog(vocab, new_token_id)) {
break;
}
char buf[128];
int n = llama_token_to_piece(model, new_token_id, buf, sizeof(buf), 0, true);
int n = llama_token_to_piece(vocab, new_token_id, buf, sizeof(buf), 0, true);
if (n < 0) {
fprintf(stderr, "%s: error: failed to convert token to piece\n", __func__);
return 1;