tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

main : honor --verbose-prompt on interactive prompts (#14350)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-06-24 09:31:00 +02:00
committed by GitHub
parent 901e20bbe5
commit abf241045d
1 changed files with 10 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tools/main/main.cpp
View File

@ -917,10 +917,19 @@ int main(int argc, char ** argv) {
embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end()); embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end());
embd_inp.insert(embd_inp.end(), line_sfx.begin(), line_sfx.end()); embd_inp.insert(embd_inp.end(), line_sfx.begin(), line_sfx.end());
if (params.verbose_prompt) {
LOG_INF("%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size() - original_size);
}
for (size_t i = original_size; i < embd_inp.size(); ++i) { for (size_t i = original_size; i < embd_inp.size(); ++i) {
const llama_token token = embd_inp[i]; const llama_token token = embd_inp[i];
const std::string token_str = common_token_to_piece(ctx, token);
output_tokens.push_back(token); output_tokens.push_back(token);
output_ss << common_token_to_piece(ctx, token); output_ss << token_str;
if (params.verbose_prompt) {
LOG_INF("%6d -> '%s'\n", token, token_str.c_str());
}
} }
// reset assistant message // reset assistant message