Q2 and Q3 quantization

Author: sw

examples/quantize/quantize.cpp

@@ -14,6 +14,8 @@ int main(int argc, char ** argv) {
         fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
         fprintf(stderr, "  type = %d - q4_0\n", LLAMA_FTYPE_MOSTLY_Q4_0);
         fprintf(stderr, "  type = %d - q4_1\n", LLAMA_FTYPE_MOSTLY_Q4_1);
+        fprintf(stderr, "  type = %d - q2_0\n", LLAMA_FTYPE_MOSTLY_Q2_0);
+        fprintf(stderr, "  type = %d - q3_0\n", LLAMA_FTYPE_MOSTLY_Q3_0);
         return 1;
     }