ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Refactor gguf scripts to improve metadata handling (#11909)

Browse source 
* Refactor gguf scripts to improve metadata handling

Added contents method to ReaderField class
Added endianess property to GGUFReader class

* update scripts

* fix import

* remove unused import

* attempt to work around flake and pyright errors

* second attempt

* give up, ignore type

* bump version

* apply newbyteorder fixes
This commit is contained in:
Sigbjørn Skjæret 2025-02-26 14:04:48 +01:00 • committed by GitHub
parent 3567ee3a94
commit 69050a11be
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 88 additions and 81 deletions
Download patch file Download diff file Expand all files Collapse all files

23
gguf-py/gguf/scripts/gguf_convert_endian.py
View file

@ -20,22 +20,15 @@ logger = logging.getLogger("gguf-convert-endian")
def convert_byteorder(reader: gguf.GGUFReader, args: argparse.Namespace) -> None:
if np.uint32(1) == np.uint32(1).newbyteorder("<"):
# Host is little endian
host_endian = "little"
swapped_endian = "big"
file_endian = reader.endianess.name
if reader.byte_order == 'S':
host_endian = 'BIG' if file_endian == 'LITTLE' else 'LITTLE'
else:
# Sorry PDP or other weird systems that don't use BE or LE.
host_endian = "big"
swapped_endian = "little"
if reader.byte_order == "S":
file_endian = swapped_endian
else:
file_endian = host_endian
order = host_endian if args.order == "native" else args.order
logger.info(f"* Host is {host_endian.upper()} endian, GGUF file seems to be {file_endian.upper()} endian")
host_endian = file_endian
order = host_endian if args.order == "native" else args.order.upper()
logger.info(f"* Host is {host_endian} endian, GGUF file seems to be {file_endian} endian")
if file_endian == order:
logger.info(f"* File is already {order.upper()} endian. Nothing to do.")
logger.info(f"* File is already {order} endian. Nothing to do.")
sys.exit(0)
logger.info("* Checking tensors for conversion compatibility")
for tensor in reader.tensors:
@ -47,7 +40,7 @@ def convert_byteorder(reader: gguf.GGUFReader, args: argparse.Namespace) -> None
gguf.GGMLQuantizationType.Q6_K,
):
raise ValueError(f"Cannot handle type {tensor.tensor_type.name} for tensor {repr(tensor.name)}")
logger.info(f"* Preparing to convert from {file_endian.upper()} to {order.upper()}")
logger.info(f"* Preparing to convert from {file_endian} to {order}")
if args.dry_run:
return
logger.warning("*** Warning *** Warning *** Warning **")

34
gguf-py/gguf/scripts/gguf_dump.py
View file

@ -9,8 +9,6 @@ import sys
from pathlib import Path
from typing import Any
import numpy as np
# Necessary to load the local gguf package
if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent.parent / 'gguf-py').exists():
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
@ -21,11 +19,11 @@ logger = logging.getLogger("gguf-dump")
def get_file_host_endian(reader: GGUFReader) -> tuple[str, str]:
host_endian = 'LITTLE' if np.uint32(1) == np.uint32(1).newbyteorder("<") else 'BIG'
file_endian = reader.endianess.name
if reader.byte_order == 'S':
file_endian = 'BIG' if host_endian == 'LITTLE' else 'LITTLE'
host_endian = 'BIG' if file_endian == 'LITTLE' else 'LITTLE'
else:
file_endian = host_endian
host_endian = file_endian
return (host_endian, file_endian)
@ -45,12 +43,20 @@ def dump_metadata(reader: GGUFReader, args: argparse.Namespace) -> None:
pretty_type = str(field.types[-1].name)
log_message = f' {n:5}: {pretty_type:10} | {len(field.data):8} | {field.name}'
if len(field.types) == 1:
if field.types:
curr_type = field.types[0]
if curr_type == GGUFValueType.STRING:
log_message += ' = {0}'.format(repr(str(bytes(field.parts[-1]), encoding='utf-8')[:60]))
elif field.types[0] in reader.gguf_scalar_to_np:
log_message += ' = {0}'.format(field.parts[-1][0])
content = field.contents()
if len(content) > 60:
content = content[:57] + '...'
log_message += ' = {0}'.format(repr(content))
elif curr_type in reader.gguf_scalar_to_np:
log_message += ' = {0}'.format(field.contents())
else:
content = repr(field.contents(slice(6)))
if len(field.data) > 6:
content = content[:-1] + ', ...]'
log_message += ' = {0}'.format(content)
print(log_message) # noqa: NP100
if args.no_tensors:
return
@ -82,15 +88,9 @@ def dump_metadata_json(reader: GGUFReader, args: argparse.Namespace) -> None:
curr["array_types"] = [t.name for t in field.types][1:]
if not args.json_array:
continue
itype = field.types[-1]
if itype == GGUFValueType.STRING:
curr["value"] = [str(bytes(field.parts[idx]), encoding="utf-8") for idx in field.data]
else:
curr["value"] = [pv for idx in field.data for pv in field.parts[idx].tolist()]
elif field.types[0] == GGUFValueType.STRING:
curr["value"] = str(bytes(field.parts[-1]), encoding="utf-8")
curr["value"] = field.contents()
else:
curr["value"] = field.parts[-1].tolist()[0]
curr["value"] = field.contents()
if not args.no_tensors:
for idx, tensor in enumerate(reader.tensors):
tensors[tensor.name] = {

43
gguf-py/gguf/scripts/gguf_new_metadata.py
View file

@ -8,7 +8,6 @@ import sys
import json
from pathlib import Path
import numpy as np
from tqdm import tqdm
from typing import Any, Sequence, NamedTuple
@ -27,45 +26,10 @@ class MetadataDetails(NamedTuple):
description: str = ''
def get_byteorder(reader: gguf.GGUFReader) -> gguf.GGUFEndian:
if np.uint32(1) == np.uint32(1).newbyteorder("<"):
# Host is little endian
host_endian = gguf.GGUFEndian.LITTLE
swapped_endian = gguf.GGUFEndian.BIG
else:
# Sorry PDP or other weird systems that don't use BE or LE.
host_endian = gguf.GGUFEndian.BIG
swapped_endian = gguf.GGUFEndian.LITTLE
if reader.byte_order == "S":
return swapped_endian
else:
return host_endian
def decode_field(field: gguf.ReaderField | None) -> Any:
if field and field.types:
main_type = field.types[0]
if main_type == gguf.GGUFValueType.ARRAY:
sub_type = field.types[-1]
if sub_type == gguf.GGUFValueType.STRING:
return [str(bytes(field.parts[idx]), encoding='utf-8') for idx in field.data]
else:
return [pv for idx in field.data for pv in field.parts[idx].tolist()]
if main_type == gguf.GGUFValueType.STRING:
return str(bytes(field.parts[-1]), encoding='utf-8')
else:
return field.parts[-1][0]
return None
def get_field_data(reader: gguf.GGUFReader, key: str) -> Any:
field = reader.get_field(key)
return decode_field(field)
return field.contents() if field else None
def find_token(token_list: Sequence[int], token: str) -> Sequence[int]:
@ -93,7 +57,7 @@ def copy_with_new_metadata(reader: gguf.GGUFReader, writer: gguf.GGUFWriter, new
logger.debug(f'Removing {field.name}')
continue
old_val = MetadataDetails(field.types[0], decode_field(field))
old_val = MetadataDetails(field.types[0], field.contents())
val = new_metadata.get(field.name, old_val)
if field.name in new_metadata:
@ -192,7 +156,6 @@ def main() -> None:
reader = gguf.GGUFReader(args.input, 'r')
arch = get_field_data(reader, gguf.Keys.General.ARCHITECTURE)
endianess = get_byteorder(reader)
token_list = get_field_data(reader, gguf.Keys.Tokenizer.LIST) or []
@ -230,7 +193,7 @@ def main() -> None:
sys.exit(0)
logger.info(f'* Writing: {args.output}')
writer = gguf.GGUFWriter(args.output, arch=arch, endianess=endianess)
writer = gguf.GGUFWriter(args.output, arch=arch, endianess=reader.endianess)
alignment = get_field_data(reader, gguf.Keys.General.ALIGNMENT)
if alignment is not None: