Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-10-29 22:20:15 +01:00
Code Issues Packages Projects Releases Wiki Activity

quantize : use unused imatrix chunk_size with LLAMA_TRACE

Browse Source
This commit is contained in:
Francis Couture-Harpin 2024-09-10 12:09:17 -04:00
parent 8c13e16bb0
commit 2d79a7077c
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/quantize/quantize.cpp
View File

@ -220,7 +220,7 @@ static int load_imatrix(const std::string & imatrix_file, std::string & imatrix_
}
}
if (getenv("LLAMA_TRACE")) {
printf("%s: loaded data (size = %6d, n_tokens = %6d) for '%s'\n", __func__, int(e.size()), int(max_count), name.c_str());
printf("%s: loaded data (size = %6d, n_tokens = %6d, n_chunks = %6d) for '%s'\n", __func__, int(e.size()), int(max_count), int(max_count / chunk_size), name.c_str());
}
}