tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add --n-predict -2 for stopping generation on full context (#2565)

Browse Source
This commit is contained in:
Christian Demsar
2023-08-10 10:28:27 -04:00
committed by GitHub
parent 1638757767
commit e59fcb2bc1
3 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/main/main.cpp
View File

@ -431,8 +431,12 @@ int main(int argc, char ** argv) {
// - take the n_keep first tokens from the original prompt (via n_past)
// - take half of the last (n_ctx - n_keep) tokens and recompute the logits in batches
if (n_past + (int) embd.size() + std::max<int>(0, guidance_offset) > n_ctx) {
const int n_left = n_past - params.n_keep;
if (params.n_predict == -2) {
fprintf(stderr, "\n\n%s: context full, stopping generation\n", __func__);
break;
}
const int n_left = n_past - params.n_keep;
// always keep the first token - BOS
n_past = std::max(1, params.n_keep);
n_past_guidance = std::max(1, params.n_keep + guidance_offset);