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

check C++ code with -Wmissing-declarations (#3184)

Browse source
This commit is contained in:
Cebtenzzre 2023-09-15 15:38:27 -04:00 • committed by GitHub
parent 69eb67e282
commit 3aefaab9e5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
22 changed files with 247 additions and 243 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/quantize/quantize.cpp
View file

@ -40,7 +40,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
};
bool try_parse_ftype(const std::string & ftype_str_in, llama_ftype & ftype, std::string & ftype_str_out) {
static bool try_parse_ftype(const std::string & ftype_str_in, llama_ftype & ftype, std::string & ftype_str_out) {
std::string ftype_str;
for (auto ch : ftype_str_in) {
@ -72,7 +72,7 @@ bool try_parse_ftype(const std::string & ftype_str_in, llama_ftype & ftype, std:
// usage:
// ./quantize [--allow-requantize] [--leave-output-tensor] models/llama/ggml-model.gguf [models/llama/ggml-model-quant.gguf] type [nthreads]
//
void usage(const char * executable) {
static void usage(const char * executable) {
printf("usage: %s [--help] [--allow-requantize] [--leave-output-tensor] model-f32.gguf [model-quant.gguf] type [nthreads]\n\n", executable);
printf(" --allow-requantize: Allows requantizing tensors that have already been quantized. Warning: This can severely reduce quality compared to quantizing from 16bit or 32bit\n");
printf(" --leave-output-tensor: Will leave output.weight un(re)quantized. Increases model size but may also increase quality, especially when requantizing\n");