gguf-py : Add tokenizer.ggml.pre to gguf-new-metadata.py (#7627)

diff --git a/gguf-py/scripts/gguf-new-metadata.py b/gguf-py/scripts/gguf-new-metadata.py
index c9f1927f6a0be0f2dce881c1f25f81c822bd94a0..21e91180cd340be33523c5b9b7686a0b3534ac07 100755 (executable)
--- a/gguf-py/scripts/gguf-new-metadata.py
+++ b/gguf-py/scripts/gguf-new-metadata.py
@@ -144,6 +144,7 @@ def main() -> None:
     parser.add_argument("--general-description",                       type=str,  help="The models general.description", metavar='"Description ..."')
     parser.add_argument("--chat-template",                             type=str,  help="Chat template string (or JSON string containing templates)", metavar='"{% ... %} ..."')
     parser.add_argument("--chat-template-config",                      type=Path, help="Config file containing chat template(s)", metavar='tokenizer_config.json')
+    parser.add_argument("--pre-tokenizer",                             type=str,  help="The models tokenizer.ggml.pre", metavar='"pre tokenizer"')
     parser.add_argument("--remove-metadata",      action="append",     type=str,  help="Remove metadata (by key name) from output model", metavar='general.url')
     parser.add_argument("--special-token",        action="append",     type=str,  help="Special token by value", nargs=2, metavar=(' | '.join(token_names.keys()), '"<token>"'))
     parser.add_argument("--special-token-by-id",  action="append",     type=str,  help="Special token by id", nargs=2, metavar=(' | '.join(token_names.keys()), '0'))
@@ -172,6 +173,9 @@ def main() -> None:
             if template:
                 new_metadata[gguf.Keys.Tokenizer.CHAT_TEMPLATE] = MetadataDetails(gguf.GGUFValueType.STRING, template)
 
+    if args.pre_tokenizer:
+        new_metadata[gguf.Keys.Tokenizer.PRE] = MetadataDetails(gguf.GGUFValueType.STRING, args.pre_tokenizer)
+
     if remove_metadata:
         logger.warning('*** Warning *** Warning *** Warning **')
         logger.warning('* Most metadata is required for a fully functional GGUF file,')