CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

simple-chat : only add bos on first prompt (#10129)

Browse Source
This commit is contained in:
Diego Devesa
2024-11-02 13:08:53 +01:00
committed by GitHub
parent 7554aa4655
commit b634f8a26f
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -96,7 +96,7 @@ int main(int argc, char ** argv) {
// tokenize the prompt // 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(model, prompt.c_str(), prompt.size(), NULL, 0, true, true);
std::vector<llama_token> prompt_tokens(n_prompt_tokens); std::vector<llama_token> prompt_tokens(n_prompt_tokens);
if (llama_tokenize(model, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), true, true) < 0) { 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) {
GGML_ABORT("failed to tokenize the prompt\n"); GGML_ABORT("failed to tokenize the prompt\n");
} }