tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-12 19:37:53 -04:00
Code Issues Packages Projects Releases Wiki Activity

If n_predict == -1, generate forever

Browse Source
This commit is contained in:
Georgi Gerganov
2023-03-25 21:51:41 +02:00
parent e2d490dafd
commit 79b2b266db
3 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/main/main.cpp
View File

@@ -199,7 +199,6 @@ int main(int argc, char ** argv) {
}
params.n_keep = std::min(params.n_keep, (int) embd_inp.size());
//params.n_predict = std::min(params.n_predict, n_ctx - (int) embd_inp.size());
// prefix & suffix for instruct mode
const auto inp_pfx = ::llama_tokenize(ctx, "\n\n### Instruction:\n\n", true);
@@ -293,7 +292,7 @@ int main(int argc, char ** argv) {
std::vector<llama_token> embd;
while (n_remain > 0 || params.interactive) {
while (n_remain != 0 || params.interactive) {
// predict
if (embd.size() > 0) {
// infinite text generation via context swapping