tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

sampling : when top-k <= 0 -> noop (#13173)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-04-29 20:22:57 +03:00
committed by GitHub
parent 5a63980117
commit d9d398f84f
2 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@ -1232,6 +1232,7 @@ extern "C" {
"will be removed in the future (see https://github.com/ggml-org/llama.cpp/pull/9896#discussion_r1800920915)");
/// @details Top-K sampling described in academic paper "The Curious Case of Neural Text Degeneration" https://arxiv.org/abs/1904.09751
/// Setting k <= 0 makes this a noop
LLAMA_API struct llama_sampler * llama_sampler_init_top_k (int32_t k);
/// @details Nucleus sampling described in academic paper "The Curious Case of Neural Text Degeneration" https://arxiv.org/abs/1904.09751