CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Respect the maximum number of tokens in interactive. (#298)

Browse Source 
Co-authored-by: Johnman <johnman@github>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
tjohnman
2023-03-19 19:31:17 +01:00
committed by GitHub
parent 50fae10d03
commit 368d0c8a9e
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
main.cpp
View File

@@ -1062,7 +1062,6 @@ int main(int argc, char ** argv) {
} }
// end of text token // end of text token
if (embd.back() == EOS_TOKEN_ID) { if (embd.back() == EOS_TOKEN_ID) {
if (params.interactive) { if (params.interactive) {
is_interacting = true; is_interacting = true;
@@ -1071,6 +1070,12 @@ int main(int argc, char ** argv) {
break; break;
} }
} }
// In interactive mode, respect the maximum number of tokens and drop back to user input when reached.
if (params.interactive && remaining_tokens <= 0) {
remaining_tokens = params.n_predict;
is_interacting = true;
}
} }
#if defined (_WIN32) #if defined (_WIN32)