convert : update mtp related help (#23334)

* update mtp related help

* remove outdated experimental text

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index ff8400508614e850be4476ea9ac959d6e3a8ec07..1d18a1bf91f6abead4bbb3f7b028e8bc42fb258f 100755 (executable)
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -115,15 +115,15 @@ def parse_args() -> argparse.Namespace:
     )
     parser.add_argument(
         "--mmproj", action="store_true",
-        help="(Experimental) Export multimodal projector (mmproj) for vision models. This will only work on some vision models. A prefix 'mmproj-' will be added to the output file name.",
+        help="Export multimodal projector (mmproj) for vision models. This will only work on some vision models. An 'mmproj-' prefix will be added to the output file name.",
     )
     parser.add_argument(
         "--mtp", action="store_true",
-        help="(Experimental) Export only the multi-token prediction (MTP) head as a separate GGUF, suitable for use as a speculative draft. Output file name will get a '-MTP' suffix.",
+        help="Export only the multi-token prediction (MTP) head as a separate GGUF, suitable for use as a speculative draft. An 'mtp-' prefix will be added to the output file name.",
     )
     parser.add_argument(
         "--no-mtp", action="store_true",
-        help="(Experimental) Exclude the multi-token prediction (MTP) head from the converted GGUF. Pair with --mtp on a second run to publish trunk and MTP as two files. Note: the split form duplicates embeddings, so the bundled default is more space-efficient overall.",
+        help="Exclude the multi-token prediction (MTP) head from the converted GGUF. Pair with --mtp on a second run to publish trunk and MTP as two files. Note: the split form duplicates embeddings, but even though the bundled default is more space-efficient overall, this allows differing quantization which may be more performant.",
     )
     parser.add_argument(
         "--mistral-format", action="store_true",