vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

quantize : terminate on errors + trace logs

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-04-03 15:18:32 +03:00
parent 822caa46a1
commit a054283c0f
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 10 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

16
examples/quantize/quantize.cpp
View file

@ -116,13 +116,13 @@ static void load_imatrix(const std::string & imatrix_file, std::unordered_map<st
std::ifstream in(imatrix_file.c_str(), std::ios::binary);
if (!in) {
printf("%s: failed to open %s\n",__func__, imatrix_file.c_str());
return;
exit(1);
}
int n_entries;
in.read((char *)&n_entries, sizeof(n_entries));
if (in.fail() || n_entries < 1) {
printf("%s: no data in file %s\n", __func__, imatrix_file.c_str());
return;
exit(1);
}
for (int i = 0; i < n_entries; ++i) {
int len; in.read((char *)&len, sizeof(len));
@ -130,11 +130,11 @@ static void load_imatrix(const std::string & imatrix_file, std::unordered_map<st
in.read((char *)name_as_vec.data(), len);
if (in.fail()) {
printf("%s: failed reading name for entry %d from %s\n", __func__, i+1, imatrix_file.c_str());
return;
exit(1);
}
name_as_vec[len] = 0;
std::string name{name_as_vec.data()};
auto & e = imatrix_data[std::move(name)];
auto & e = imatrix_data[name];
int ncall;
in.read((char *)&ncall, sizeof(ncall));
int nval;
@ -142,18 +142,22 @@ static void load_imatrix(const std::string & imatrix_file, std::unordered_map<st
if (in.fail() || nval < 1) {
printf("%s: failed reading number of values for entry %d\n", __func__, i);
imatrix_data = {};
return;
exit(1);
}
e.resize(nval);
in.read((char *)e.data(), nval*sizeof(float));
if (in.fail()) {
printf("%s: failed reading data for entry %d\n", __func__, i);
imatrix_data = {};
return;
exit(1);
}
if (ncall > 0) {
for (auto& v : e) v /= ncall;
}
if (getenv("LLAMA_TRACE")) {
printf("%s: loaded data (size = %6d, ncall = %6d) for '%s'\n", __func__, int(e.size()), ncall, name.c_str());
}
}
printf("%s: loaded %d importance matrix entries from %s\n", __func__, int(imatrix_data.size()), imatrix_file.c_str());
}