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

examples : rely on new behavior of add_special

Browse source
This commit is contained in:
Jared Van Bortel 2024-04-04 18:12:33 -04:00
parent d1a1b614cd
commit 92591c125f
14 changed files with 53 additions and 69 deletions
Download patch file Download diff file Expand all files Collapse all files

16
common/common.cpp
View file

@ -2141,23 +2141,23 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
std::vector<llama_token> llama_tokenize(
const struct llama_context * ctx,
const std::string & text,
bool add_bos,
bool special) {
return llama_tokenize(llama_get_model(ctx), text, add_bos, special);
bool add_special,
bool parse_special) {
return llama_tokenize(llama_get_model(ctx), text, add_special, parse_special);
}
std::vector<llama_token> llama_tokenize(
const struct llama_model * model,
const std::string & text,
bool add_bos,
bool special) {
bool add_special,
bool parse_special) {
// upper limit for the number of tokens
int n_tokens = text.length() + add_bos;
int n_tokens = text.length() + 2 * add_special;
std::vector<llama_token> result(n_tokens);
n_tokens = llama_tokenize(model, text.data(), text.length(), result.data(), result.size(), add_bos, special);
n_tokens = llama_tokenize(model, text.data(), text.length(), result.data(), result.size(), add_special, parse_special);
if (n_tokens < 0) {
result.resize(-n_tokens);
int check = llama_tokenize(model, text.data(), text.length(), result.data(), result.size(), add_bos, special);
int check = llama_tokenize(model, text.data(), text.length(), result.data(), result.size(), add_special, parse_special);
GGML_ASSERT(check == -n_tokens);
} else {
result.resize(n_tokens);

8
common/common.h
View file

@ -221,14 +221,14 @@ void llama_batch_add(
std::vector<llama_token> llama_tokenize(
const struct llama_context * ctx,
const std::string & text,
bool add_bos,
bool special = false);
bool add_special,
bool parse_special = false);
std::vector<llama_token> llama_tokenize(
const struct llama_model * model,
const std::string & text,
bool add_bos,
bool special = false);
bool add_special,
bool parse_special = false);
// tokenizes a token into a piece
// should work similar to Python's `tokenizer.id_to_piece`