haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests 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
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 1 deletions
Show stats 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
if (embd.back() == EOS_TOKEN_ID) {
if (params.interactive) {
is_interacting = true;
@ -1071,6 +1070,12 @@ int main(int argc, char ** argv) {
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)