vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

gguf-dump: add --data-offset

Browse source
This commit is contained in:
brian khuu 2024-06-21 20:23:34 +10:00 • committed by Brian
parent 9a590c8226
commit b664c3cad7
2 changed files with 6 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
gguf-py/gguf/gguf_reader.py
View file

@ -69,6 +69,7 @@ class GGUFReader:
# I - same as host, S - swapped # I - same as host, S - swapped
byte_order: Literal['I'] | Literal['S'] = 'I' byte_order: Literal['I'] | Literal['S'] = 'I'
alignment: int = GGUF_DEFAULT_ALIGNMENT alignment: int = GGUF_DEFAULT_ALIGNMENT
start_data_offset: int
# Note: Internal helper, API may change. # Note: Internal helper, API may change.
gguf_scalar_to_np: dict[GGUFValueType, type[np.generic]] = { gguf_scalar_to_np: dict[GGUFValueType, type[np.generic]] = {
@ -117,6 +118,7 @@ class GGUFReader:
padding = offs % self.alignment padding = offs % self.alignment
if padding != 0: if padding != 0:
offs += self.alignment - padding offs += self.alignment - padding
self.start_data_offset = offs
self._build_tensors(offs, tensors_fields) self._build_tensors(offs, tensors_fields)
_DT = TypeVar('_DT', bound = npt.DTypeLike) _DT = TypeVar('_DT', bound = npt.DTypeLike)

5
gguf-py/scripts/gguf-dump.py
View file

@ -364,6 +364,7 @@ def main() -> None:
parser.add_argument("--no-tensors", action="store_true", help="Don't dump tensor metadata") parser.add_argument("--no-tensors", action="store_true", help="Don't dump tensor metadata")
parser.add_argument("--json", action="store_true", help="Produce JSON output") parser.add_argument("--json", action="store_true", help="Produce JSON output")
parser.add_argument("--json-array", action="store_true", help="Include full array values in JSON output (long)") parser.add_argument("--json-array", action="store_true", help="Include full array values in JSON output (long)")
parser.add_argument("--data-offset", action="store_true", help="Start of data offset")
parser.add_argument("--markdown", action="store_true", help="Produce markdown output") parser.add_argument("--markdown", action="store_true", help="Produce markdown output")
parser.add_argument("--verbose", action="store_true", help="increase output verbosity") parser.add_argument("--verbose", action="store_true", help="increase output verbosity")
@ -371,7 +372,7 @@ def main() -> None:
logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO) logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO)
if not args.json and not args.markdown: if not args.json and not args.markdown and not args.data_offset:
logger.info(f'* Loading: {args.model}') logger.info(f'* Loading: {args.model}')
reader = GGUFReader(args.model, 'r') reader = GGUFReader(args.model, 'r')
@ -380,6 +381,8 @@ def main() -> None:
dump_metadata_json(reader, args) dump_metadata_json(reader, args)
elif args.markdown: elif args.markdown:
dump_markdown_metadata(reader, args) dump_markdown_metadata(reader, args)
elif args.data_offset:
print(reader.start_data_offset)
else: else:
dump_metadata(reader, args) dump_metadata(reader, args)