tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 11:45:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

examples : fix is_first logic for tokenization (#14329)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-22 20:10:07 +03:00
committed by GitHub
parent af3373f1ad
commit f1f5e82df6
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/simple-chat/simple-chat.cpp
View File

@ -98,7 +98,7 @@ int main(int argc, char ** argv) {
auto generate = [&](const std::string & prompt) {
std::string response;
const bool is_first = llama_memory_seq_pos_max(llama_get_memory(ctx), 0) == 0;
const bool is_first = llama_memory_seq_pos_max(llama_get_memory(ctx), 0) == -1;
// tokenize the prompt
const int n_prompt_tokens = -llama_tokenize(vocab, prompt.c_str(), prompt.size(), NULL, 0, is_first, true);

2
tools/run/run.cpp
View File

@ -939,7 +939,7 @@ static int apply_chat_template(const struct common_chat_templates * tmpls, Llama
// Function to tokenize the prompt
static int tokenize_prompt(const llama_vocab * vocab, const std::string & prompt,
std::vector<llama_token> & prompt_tokens, const LlamaData & llama_data) {
const bool is_first = llama_memory_seq_pos_max(llama_get_memory(llama_data.context.get()), 0) == 0;
const bool is_first = llama_memory_seq_pos_max(llama_get_memory(llama_data.context.get()), 0) == -1;
const int n_prompt_tokens = -llama_tokenize(vocab, prompt.c_str(), prompt.size(), NULL, 0, is_first, true);
prompt_tokens.resize(n_prompt_tokens);