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

convert.py : add python logging instead of print() (#6511)

Browse source 
* convert.py: add python logging instead of print()

* convert.py: verbose flag takes priority over dump flag log suppression

* convert.py: named instance logging

* convert.py: use explicit logger id string

* convert.py: convert extra print() to named logger

* convert.py: sys.stderr.write --> logger.error

* *.py: Convert all python scripts to use logging module

* requirements.txt: remove extra line

* flake8: update flake8 ignore and exclude to match ci settings

* gh-actions: add flake8-no-print to flake8 lint step

* pre-commit: add flake8-no-print to flake8 and also update pre-commit version

* convert-hf-to-gguf.py: print() to logger conversion

* *.py: logging basiconfig refactor to use conditional expression

* *.py: removed commented out logging

* fixup! *.py: logging basiconfig refactor to use conditional expression

* constant.py: logger.error then exit should be a raise exception instead

* *.py: Convert logger error and sys.exit() into a raise exception (for atypical error)

* gguf-convert-endian.py: refactor convert_byteorder() to use tqdm progressbar

* verify-checksum-model.py: This is the result of the program, it should be printed to stdout.

* compare-llama-bench.py: add blank line for readability during missing repo response

* reader.py: read_gguf_file() use print() over logging

* convert.py: warning goes to stderr and won't hurt the dump output

* gguf-dump.py: dump_metadata() should print to stdout

* convert-hf-to-gguf.py: print --> logger.debug or ValueError()

* verify-checksum-models.py: use print() for printing table

* *.py: refactor logging.basicConfig()

* gguf-py/gguf/*.py: use __name__ as logger name

Since they will be imported and not run directly.

* python-lint.yml: use .flake8 file instead

* constants.py: logger no longer required

* convert-hf-to-gguf.py: add additional logging

* convert-hf-to-gguf.py: print() --> logger

* *.py: fix flake8 warnings

* revert changes to convert-hf-to-gguf.py for get_name()

* convert-hf-to-gguf-update.py: use triple quoted f-string instead

* *.py: accidentally corrected the wrong line

* *.py: add compilade warning suggestions and style fixes
This commit is contained in:
Brian 2024-05-04 05:36:41 +10:00 • committed by GitHub
parent 433def286e
commit a2ac89d6ef
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 536 additions and 482 deletions
Download patch file Download diff file Expand all files Collapse all files

29
gguf-py/scripts/gguf-dump.py
View file

@ -1,6 +1,7 @@
#!/usr/bin/env python3
from __future__ import annotations
import logging
import argparse
import os
import sys
@ -15,6 +16,8 @@ if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent /
from gguf import GGUFReader, GGUFValueType # noqa: E402
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'
@ -29,8 +32,8 @@ def get_file_host_endian(reader: GGUFReader) -> tuple[str, str]:
# please see the comments in the modify_gguf.py example.
def dump_metadata(reader: GGUFReader, args: argparse.Namespace) -> None:
host_endian, file_endian = get_file_host_endian(reader)
print(f'* File is {file_endian} endian, script is running on a {host_endian} endian host.')
print(f'\n* Dumping {len(reader.fields)} key/value pair(s)')
print(f'* File is {file_endian} endian, script is running on a {host_endian} endian host.') # noqa: NP100
print(f'* Dumping {len(reader.fields)} key/value pair(s)') # noqa: NP100
for n, field in enumerate(reader.fields.values(), 1):
if not field.types:
pretty_type = 'N/A'
@ -39,20 +42,21 @@ def dump_metadata(reader: GGUFReader, args: argparse.Namespace) -> None:
pretty_type = '[' * nest_count + str(field.types[-1].name) + ']' * nest_count
else:
pretty_type = str(field.types[-1].name)
print(f' {n:5}: {pretty_type:10} | {len(field.data):8} | {field.name}', end = '')
log_message = f' {n:5}: {pretty_type:10} | {len(field.data):8} | {field.name}'
if len(field.types) == 1:
curr_type = field.types[0]
if curr_type == GGUFValueType.STRING:
print(' = {0}'.format(repr(str(bytes(field.parts[-1]), encoding='utf8')[:60])), end = '')
log_message += ' = {0}'.format(repr(str(bytes(field.parts[-1]), encoding='utf8')[:60]))
elif field.types[0] in reader.gguf_scalar_to_np:
print(' = {0}'.format(field.parts[-1][0]), end = '')
print()
log_message += ' = {0}'.format(field.parts[-1][0])
print(log_message) # noqa: NP100
if args.no_tensors:
return
print(f'\n* Dumping {len(reader.tensors)} tensor(s)')
print(f'* Dumping {len(reader.tensors)} tensor(s)') # noqa: NP100
for n, tensor in enumerate(reader.tensors, 1):
prettydims = ', '.join('{0:5}'.format(d) for d in list(tensor.shape) + [1] * (4 - len(tensor.shape)))
print(f' {n:5}: {tensor.n_elements:10} | {prettydims} | {tensor.tensor_type.name:7} | {tensor.name}')
print(f' {n:5}: {tensor.n_elements:10} | {prettydims} | {tensor.tensor_type.name:7} | {tensor.name}') # noqa: NP100
def dump_metadata_json(reader: GGUFReader, args: argparse.Namespace) -> None:
@ -103,10 +107,17 @@ def main() -> None:
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-array", action="store_true", help="Include full array values in JSON output (long)")
parser.add_argument("--verbose", action="store_true", help="increase output verbosity")
args = parser.parse_args(None if len(sys.argv) > 1 else ["--help"])
logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO)
if not args.json:
print(f'* Loading: {args.model}')
logger.info(f'* Loading: {args.model}')
reader = GGUFReader(args.model, 'r')
if args.json:
dump_metadata_json(reader, args)
else: