Function usage

smallthinker/tools/quantize/quantize.cpp:113–141

usage: ./llama-quantize [--allow-requantize] [--leave-output-tensor] [--pure] models/llama/ggml-model.gguf [models/llama/ggml-model-quant.gguf] type [nthreads]

//  ./llama-quantize [--allow-requantize] [--leave-output-tensor] [--pure] models/llama/ggml-model.gguf [models/llama/ggml-model-quant.gguf] type [nthreads]
//
[[noreturn]]
static void usage(const char * executable) {
    printf("usage: %s [--help] [--allow-requantize] [--leave-output-tensor] [--pure] [--imatrix] [--include-weights] [--exclude-weights] [--output-tensor-type]\n", executable);
    printf("       [--token-embedding-type] [--tensor-type] [--keep-split] [--override-kv] model-f32.gguf [model-quant.gguf] type [nthreads]\n\n");
    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");
    printf("  --pure: Disable k-quant mixtures and quantize all tensors to the same type\n");
    printf("  --imatrix file_name: use data in file_name as importance matrix for quant optimizations\n");
    printf("  --include-weights tensor_name: use importance matrix for this/these tensor(s)\n");
    printf("  --exclude-weights tensor_name: use importance matrix for this/these tensor(s)\n");
    printf("  --output-tensor-type ggml_type: use this ggml_type for the output.weight tensor\n");
    printf("  --token-embedding-type ggml_type: use this ggml_type for the token embeddings tensor\n");
    printf("  --tensor-type TENSOR=TYPE: quantize this tensor to this ggml_type. example: --tensor-type attn_q=q8_0\n");
    printf("      Advanced option to selectively quantize tensors. May be specified multiple times.\n");
    printf("  --keep-split: will generate quantized model in the same shards as input\n");
    printf("  --override-kv KEY=TYPE:VALUE\n");
    printf("      Advanced option to override model metadata by key in the quantized model. May be specified multiple times.\n");
    printf("Note: --include-weights and --exclude-weights cannot be used together\n");
    printf("\nAllowed quantization types:\n");
    for (auto & it : QUANT_OPTIONS) {
        if (it.name != "COPY") {
            printf("  %2d  or  ", it.ftype);
        } else {
            printf("          ");
        }
        printf("%-7s : %s\n", it.name.c_str(), it.desc.c_str());
    }
    exit(1);
}

static int load_imatrix(const std::string & imatrix_file, std::string & imatrix_dataset, std::unordered_map<std::string, std::vector<float>> & imatrix_data) {
    std::ifstream in(imatrix_file.c_str(), std::ios::binary);