diff options
Diffstat (limited to 'examples/quantize/quantize.cpp')
| -rw-r--r-- | examples/quantize/quantize.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 1bf18248..300788c9 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -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"); |