tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 04:15:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

sampling: fix top_k <= 0 (#5388)

Browse Source 
* sampling: fix top_k <= 0

* Update llama.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Johannes Gäßler
2024-02-08 09:46:30 +01:00
committed by GitHub
parent 8504d2d0da
commit 26d4efd11e
3 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/sampling.cpp
View File

@ -132,7 +132,7 @@ static void sampler_queue(
const float temp = params.temp;
const float dynatemp_range = params.dynatemp_range;
const float dynatemp_exponent = params.dynatemp_exponent;
const int32_t top_k = params.top_k <= 0 ? n_vocab : params.top_k;
const int32_t top_k = params.top_k;
const float top_p = params.top_p;
const float min_p = params.min_p;
const float tfs_z = params.tfs_z;