You can not select more than 25 topics
Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
2.2 kB
2.2 kB
LLamaQuantizer
Namespace: LLama
The quantizer to quantize the model.
public static class LLamaQuantizer
Inheritance Object → LLamaQuantizer
Methods
Quantize(String, String, LLamaFtype, Int32)
Quantize the model.
public static bool Quantize(string srcFileName, string dstFilename, LLamaFtype ftype, int nthread)
Parameters
srcFileName String
The model file to be quantized.
dstFilename String
The path to save the quantized model.
ftype LLamaFtype
The type of quantization.
nthread Int32
Thread to be used during the quantization. By default it's the physical core number.
Returns
Boolean
Whether the quantization is successful.
Exceptions
Quantize(String, String, String, Int32)
Quantize the model.
public static bool Quantize(string srcFileName, string dstFilename, string ftype, int nthread)
Parameters
srcFileName String
The model file to be quantized.
dstFilename String
The path to save the quantized model.
ftype String
The type of quantization.
nthread Int32
Thread to be used during the quantization. By default it's the physical core number.
Returns
Boolean
Whether the quantization is successful.