root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 02:14:35 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

llama : fix typical sampling (#4261)

Browse Source 
Typical sampling was broken because after copying new_candidates into canditates, the "sorted" bool is left at "true", but the new data is no longer sorted according to probability. Patch to set "sorted" to false.

Test: Generating with temp=0.0001 (approx. argmax)  should generate the same sequence at typical>=1.0 and typical=0.9999 (approx. disabled, but enters the typical sampling codepath).
This commit is contained in:
tarcey 2023-11-30 22:40:23 +01:00 committed by GitHub
parent e2bd725f4b
commit 954e22858c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llama.cpp
View File

@ -7027,6 +7027,7 @@ void llama_sample_typical(struct llama_context * ctx, llama_token_data_array * c
// Replace the data in candidates with the new_candidates data
std::copy(new_candidates.begin(), new_candidates.end(), candidates->data);
candidates->size = new_candidates.size();
candidates->sorted = false;
if (ctx) {
ctx->t_sample_us += ggml_time_us() - t_start_sample_us;