tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 20:29:41 -04:00
Code Issues Packages Projects Releases Wiki Activity

quantize : fix using combined imatrix GGUFs (multiple datasets) (#14973)

Browse Source
This commit is contained in:
Ed Addario
2025-07-30 20:11:56 +01:00
committed by GitHub
parent 41e78c567e
commit e9192bec56
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/quantize/quantize.cpp
View File

@@ -311,7 +311,7 @@ static int load_imatrix(const std::string & imatrix_file, std::vector<std::strin
int64_t n_datasets = gguf_get_arr_n(ctx_gguf, dataset_idx); int64_t n_datasets = gguf_get_arr_n(ctx_gguf, dataset_idx);
imatrix_datasets.reserve(n_datasets); imatrix_datasets.reserve(n_datasets);
for (int64_t i = 0; i < n_datasets; ++i) { for (int64_t i = 0; i < n_datasets; ++i) {
imatrix_datasets.push_back(gguf_get_val_str(ctx_gguf, dataset_idx)); imatrix_datasets.push_back(gguf_get_arr_str(ctx_gguf, dataset_idx, i));
} }
printf("%s: imatrix datasets=['%s'", __func__, imatrix_datasets[0].c_str()); printf("%s: imatrix datasets=['%s'", __func__, imatrix_datasets[0].c_str());
for (size_t i = 1; i < imatrix_datasets.size(); ++i) { for (size_t i = 1; i < imatrix_datasets.size(); ++i) {