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

server : avoid aniprompt in probabilities of final response (#2849)

Browse Source
This commit is contained in:
Jhen-Jie Hong
2023-09-02 08:31:46 +08:00
committed by GitHub
parent f04d002844
commit 571083f508
1 changed files with 12 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
examples/server/server.cpp
View File

@@ -1379,7 +1379,13 @@ int main(int argc, char **argv)
} }
} }
const json data = format_final_response(llama, llama.generated_text, llama.generated_token_probs); auto probs = llama.generated_token_probs;
if (llama.params.n_probs > 0 && llama.stopped_word) {
const std::vector<llama_token> stop_word_toks = llama_tokenize(llama.ctx, llama.stopping_word, false);
probs = std::vector<completion_token_output>(llama.generated_token_probs.begin(), llama.generated_token_probs.end() - stop_word_toks.size());
}
const json data = format_final_response(llama, llama.generated_text, probs);
llama_print_timings(llama.ctx); llama_print_timings(llama.ctx);
@@ -1456,7 +1462,11 @@ int main(int argc, char **argv)
if (!llama.has_next_token) { if (!llama.has_next_token) {
// Generation is done, send extra information. // Generation is done, send extra information.
const json data = format_final_response(llama, "", llama.generated_token_probs); const json data = format_final_response(
llama,
"",
std::vector<completion_token_output>(llama.generated_token_probs.begin(), llama.generated_token_probs.begin() + sent_token_probs_index)
);
const std::string str = const std::string str =
"data: " + "data: " +