CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

sampling : same for typical sampling

Browse Source
This commit is contained in:
Georgi Gerganov
2025-05-27 11:30:24 +03:00
parent fe12a5d47e
commit 76f31abe53
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-sampling.cpp
View File

@@ -909,7 +909,7 @@ static void llama_sampler_typical_apply(struct llama_sampler * smpl, llama_token
cum_sum += cur_p->data[idx].p;
// Check if the running sum is greater than typical or if we have kept at least min_keep tokens
if (cum_sum > ctx->p && i >= ctx->min_keep - 1) {
if (cum_sum > ctx->p && (ctx->min_keep == 0 || i >= ctx->min_keep - 1)) {
last_idx = i + 1;
break;
}