Skip to content

Commit 6e89c8e

Browse files
authored
support inverse chat template
1 parent 2590964 commit 6e89c8e

File tree

1 file changed

+18
-5
lines changed

1 file changed

+18
-5
lines changed

gguf-py/scripts/gguf_new_metadata.py

Lines changed: 18 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -85,7 +85,8 @@ def copy_with_new_metadata(reader: gguf.GGUFReader, writer: gguf.GGUFWriter, new
8585
continue
8686

8787
# Skip old chat templates if we have new ones
88-
if field.name.startswith(gguf.Keys.Tokenizer.CHAT_TEMPLATE) and gguf.Keys.Tokenizer.CHAT_TEMPLATE in new_metadata:
88+
if (field.name.startswith(gguf.Keys.Tokenizer.CHAT_TEMPLATE) and gguf.Keys.Tokenizer.CHAT_TEMPLATE in new_metadata) \
89+
or (field.name.startswith(gguf.Keys.Tokenizer.INVERSE_TEMPLATE) and gguf.Keys.Tokenizer.INVERSE_TEMPLATE in new_metadata):
8990
logger.debug(f'Skipping {field.name}')
9091
continue
9192

@@ -110,6 +111,11 @@ def copy_with_new_metadata(reader: gguf.GGUFReader, writer: gguf.GGUFWriter, new
110111
writer.add_chat_template(new_metadata[gguf.Keys.Tokenizer.CHAT_TEMPLATE].value)
111112
del new_metadata[gguf.Keys.Tokenizer.CHAT_TEMPLATE]
112113

114+
if gguf.Keys.Tokenizer.INVERSE_TEMPLATE in new_metadata:
115+
logger.debug('Adding inverse template(s)')
116+
writer.add_inverse_template(new_metadata[gguf.Keys.Tokenizer.INVERSE_TEMPLATE].value)
117+
del new_metadata[gguf.Keys.Tokenizer.INVERSE_TEMPLATE]
118+
113119
for key, val in new_metadata.items():
114120
logger.debug(f'Adding {key}: "{val.value}" {val.description}')
115121
writer.add_key_value(key, val.value, val.type)
@@ -143,7 +149,8 @@ def main() -> None:
143149
parser.add_argument("--general-name", type=str, help="The models general.name", metavar='"name"')
144150
parser.add_argument("--general-description", type=str, help="The models general.description", metavar='"Description ..."')
145151
parser.add_argument("--chat-template", type=str, help="Chat template string (or JSON string containing templates)", metavar='"{% ... %} ..."')
146-
parser.add_argument("--chat-template-config", type=Path, help="Config file containing chat template(s)", metavar='tokenizer_config.json')
152+
parser.add_argument("--inverse-template", type=str, help="Inverse template string", metavar='"{% ... %} ..."')
153+
parser.add_argument("--chat-template-config", type=Path, help="Config file containing chat and/or inverse template(s)", metavar='tokenizer_config.json')
147154
parser.add_argument("--pre-tokenizer", type=str, help="The models tokenizer.ggml.pre", metavar='"pre tokenizer"')
148155
parser.add_argument("--remove-metadata", action="append", type=str, help="Remove metadata (by key name) from output model", metavar='general.url')
149156
parser.add_argument("--special-token", action="append", type=str, help="Special token by value", nargs=2, metavar=(' | '.join(token_names.keys()), '"<token>"'))
@@ -166,12 +173,18 @@ def main() -> None:
166173
if args.chat_template:
167174
new_metadata[gguf.Keys.Tokenizer.CHAT_TEMPLATE] = MetadataDetails(gguf.GGUFValueType.STRING, json.loads(args.chat_template) if args.chat_template.startswith('[') else args.chat_template)
168175

176+
if args.inverse_template:
177+
new_metadata[gguf.Keys.Tokenizer.INVERSE_TEMPLATE] = MetadataDetails(gguf.GGUFValueType.STRING, args.inverse_template)
178+
169179
if args.chat_template_config:
170180
with open(args.chat_template_config, 'r') as fp:
171181
config = json.load(fp)
172-
template = config.get('chat_template')
173-
if template:
174-
new_metadata[gguf.Keys.Tokenizer.CHAT_TEMPLATE] = MetadataDetails(gguf.GGUFValueType.STRING, template)
182+
chat_template = config.get('chat_template')
183+
inverse_template = config.get('inverse_template')
184+
if chat_template:
185+
new_metadata[gguf.Keys.Tokenizer.CHAT_TEMPLATE] = MetadataDetails(gguf.GGUFValueType.STRING, chat_template)
186+
if inverse_template:
187+
new_metadata[gguf.Keys.Tokenizer.INVERSE_TEMPLATE] = MetadataDetails(gguf.GGUFValueType.STRING, inverse_template)
175188

176189
if args.pre_tokenizer:
177190
new_metadata[gguf.Keys.Tokenizer.PRE] = MetadataDetails(gguf.GGUFValueType.STRING, args.pre_tokenizer)

0 commit comments

Comments
 (0)