CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

quantize : fix dataset name loading from gguf imatrix

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-06-23 12:43:25 -04:00
parent 43cd2b3eb5
commit 0e79355075
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tools/quantize/quantize.cpp
View File

@@ -206,7 +206,7 @@ static int load_legacy_imatrix(const std::string & imatrix_file, std::vector<std
}
}
// latest imatrix version contains the dataset filename at the end of the file
// latest legacy imatrix version contains the dataset filename at the end of the file
int m_last_call = 0;
if (in.peek() != EOF) {
in.read((char *)&m_last_call, sizeof(m_last_call));
@@ -318,7 +318,7 @@ static int load_imatrix(const std::string & imatrix_file, std::vector<std::strin
int m_last_chunk = gguf_get_val_u32(ctx_gguf, chunk_count_idx);
int64_t n_datasets = gguf_get_arr_n(ctx_gguf, dataset_idx);
imatrix_datasets.resize(n_datasets);
imatrix_datasets.reserve(n_datasets);
for (int64_t i = 0; i < n_datasets; ++i) {
imatrix_datasets.push_back(gguf_get_val_str(ctx_gguf, dataset_idx));
}