llama : warn when quantizing to DT3

The reference-quantizer disclaimer only existed in the code and in
llama-quantize --help; now it is also printed where the mistake would
actually be made, at the start of a quantization run targeting DT3.

src/llama-quant.cpp

@@ -884,6 +884,11 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
         throw std::runtime_error(format("invalid output file type %d\n", ftype));
     }
 
+    if (ftype == LLAMA_FTYPE_MOSTLY_DT3) {
+        LLAMA_LOG_WARN("%s: DT3 is being quantized with the in-tree REFERENCE quantizer only - "
+                       "the measured DT3 quality requires the planes from ternaria's PTQTP pipeline\n", __func__);
+    }
+
     // mmap consistently increases speed on Linux, and also increases speed on Windows with
     // hot cache. It may cause a slowdown on macOS, possibly related to free memory.
 #if defined(__linux__) || defined(_WIN32)