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

20
examples/simple-chat/simple-chat.cpp
View file

@ -75,12 +75,14 @@ int main(int argc, char ** argv) {
return 1;
}
const llama_vocab * vocab = llama_model_get_vocab(model);
// initialize the context
llama_context_params ctx_params = llama_context_default_params();
ctx_params.n_ctx = n_ctx;
ctx_params.n_batch = n_ctx;
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 , "%s: error: failed to create the llama_context\n" , __func__);
return 1;
@ -97,9 +99,9 @@ int main(int argc, char ** argv) {
std::string response;
// tokenize the prompt
const int n_prompt_tokens = -llama_tokenize(model, prompt.c_str(), prompt.size(), NULL, 0, true, true);
const int n_prompt_tokens = -llama_tokenize(vocab, prompt.c_str(), prompt.size(), NULL, 0, true, true);
std::vector<llama_token> prompt_tokens(n_prompt_tokens);
if (llama_tokenize(model, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), llama_get_kv_cache_used_cells(ctx) == 0, true) < 0) {
if (llama_tokenize(vocab, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), llama_get_kv_cache_used_cells(ctx) == 0, true) < 0) {
GGML_ABORT("failed to tokenize the prompt\n");
}
@ -124,13 +126,13 @@ 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;
}
// convert the token to a string, print it and add it to the response
char buf[256];
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) {
GGML_ABORT("failed to convert token to piece\n");
}
@ -159,12 +161,14 @@ int main(int argc, char ** argv) {
break;
}
const char * tmpl = llama_model_chat_template(model);
// add the user input to the message list and format it
messages.push_back({"user", strdup(user.c_str())});
int new_len = llama_chat_apply_template(model, nullptr, messages.data(), messages.size(), true, formatted.data(), formatted.size());
int new_len = llama_chat_apply_template(tmpl, messages.data(), messages.size(), true, formatted.data(), formatted.size());
if (new_len > (int)formatted.size()) {
formatted.resize(new_len);
new_len = llama_chat_apply_template(model, nullptr, messages.data(), messages.size(), true, formatted.data(), formatted.size());
new_len = llama_chat_apply_template(tmpl, messages.data(), messages.size(), true, formatted.data(), formatted.size());
}
if (new_len < 0) {
fprintf(stderr, "failed to apply the chat template\n");
@ -181,7 +185,7 @@ int main(int argc, char ** argv) {
// add the response to the messages
messages.push_back({"assistant", strdup(response.c_str())});
prev_len = llama_chat_apply_template(model, nullptr, messages.data(), messages.size(), false, nullptr, 0);
prev_len = llama_chat_apply_template(tmpl, messages.data(), messages.size(), false, nullptr, 0);
if (prev_len < 0) {
fprintf(stderr, "failed to apply the chat template\n");
return 1;