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

server: fix reported top tokens for temperature 0 (#7203)

Browse source
This commit is contained in:
Johannes Gäßler 2024-05-11 10:11:28 +02:00 • committed by GitHub
parent b83cc3f5b3
commit 5ae3426b0b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/sampling.h
View file

@ -81,7 +81,7 @@ struct llama_sampling_context {
// TODO: replace with ring-buffer
std::vector<llama_token> prev;
std::vector<llama_token_data> cur;
size_t n_considered;
size_t n_valid; // Number of correct top tokens with correct probabilities.
std::mt19937 rng;
};