vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix #5657: force greedy sampling with probs when temp is 0

Browse source
This commit is contained in:
Minsoo Cheong 2024-02-22 14:46:19 +09:00
parent a9335a5c2a
commit 4694edde14
1 changed files with 3 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/speculative/speculative.cpp
View file

@ -167,6 +167,9 @@ int main(int argc, char ** argv) {
std::vector<seq_draft> drafts(n_seq_dft);
params.sparams.grammar.clear(); // the draft samplers will copy the target sampler's grammar
if (params.sparams.temp == 0) {
params.sparams.temp = -1.0f; // force greedy sampling with probs for the draft model
}
for (int s = 0; s < n_seq_dft; ++s) {
drafts[s].ctx_sampling = llama_sampling_init(params.sparams);