summaryrefslogtreecommitdiff
path: root/convert-persimmon-to-gguf.py
diff options
context:
space:
mode:
authorBrian <mofosyne@gmail.com>2024-05-04 05:36:41 +1000
committerGitHub <noreply@github.com>2024-05-03 22:36:41 +0300
commita2ac89d6efb41b535778bfeaecaae8fe295b6ed3 (patch)
tree584a6f5316a627e64bfbc3aa5e098b911aef285a /convert-persimmon-to-gguf.py
parent433def286e98751bf17db75dce53847d075c0be5 (diff)
convert.py : add python logging instead of print() (#6511)
* 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
Diffstat (limited to 'convert-persimmon-to-gguf.py')
-rwxr-xr-xconvert-persimmon-to-gguf.py28
1 files changed, 16 insertions, 12 deletions
diff --git a/convert-persimmon-to-gguf.py b/convert-persimmon-to-gguf.py
index aba57542..07dcade7 100755
--- a/convert-persimmon-to-gguf.py
+++ b/convert-persimmon-to-gguf.py
@@ -1,6 +1,7 @@
#!/usr/bin/env python3
from __future__ import annotations
+import logging
import argparse
import os
import sys
@@ -14,6 +15,8 @@ if 'NO_LOCAL_GGUF' not in os.environ:
sys.path.insert(1, str(Path(__file__).parent / 'gguf-py'))
import gguf
+logger = logging.getLogger("persimmon-to-gguf")
+
def _flatten_dict(dct, tensors, prefix=None):
assert isinstance(dct, dict)
@@ -30,9 +33,9 @@ def _flatten_dict(dct, tensors, prefix=None):
def _get_sentencepiece_tokenizer_info(dir_model: Path):
tokenizer_path = dir_model / 'adept_vocab.model'
- print('gguf: getting sentencepiece tokenizer from', tokenizer_path)
+ logger.info('getting sentencepiece tokenizer from', tokenizer_path)
tokenizer = SentencePieceProcessor(str(tokenizer_path))
- print('gguf: adding tokens')
+ logger.info('adding tokens')
tokens: list[bytes] = []
scores: list[float] = []
toktypes: list[int] = []
@@ -67,8 +70,10 @@ def main():
parser.add_argument("--outfile", type=Path, help="path to write to; default: based on input")
parser.add_argument("--ckpt-path", type=Path, help="path to persimmon checkpoint .pt file")
parser.add_argument("--model-dir", type=Path, help="directory containing model e.g. 8b_chat_model_release")
- parser.add_argument("--adept-inference-dir", type=str, help="path to adept-inference code directory")
+ parser.add_argument("--adept-inference-dir", type=str, help="path to adept-inference code directory")
+ parser.add_argument("--verbose", action="store_true", help="increase output verbosity")
args = parser.parse_args()
+ logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO)
sys.path.append(str(args.adept_inference_dir))
persimmon_model = torch.load(args.ckpt_path)
hparams = persimmon_model['args']
@@ -107,7 +112,7 @@ def main():
gguf_writer.add_eos_token_id(71013)
tensor_map = gguf.get_tensor_name_map(arch, block_count)
- print(tensor_map)
+ logger.info(tensor_map)
for name in tensors.keys():
data_torch = tensors[name]
if name.endswith(".self_attention.rotary_emb.inv_freq"):
@@ -117,22 +122,21 @@ def main():
data = data_torch.to(torch.float32).squeeze().numpy()
new_name = tensor_map.get_name(name, try_suffixes = (".weight", ".bias"))
if new_name is None:
- print("Can not map tensor '" + name + "'")
- sys.exit()
+ raise ValueError(f"Can not map tensor '{name}'")
+
n_dims = len(data.shape)
- print(new_name + ", n_dims = " + str(n_dims) + ", " + str(old_dtype) + " --> " + str(data.dtype))
+ logger.debug(f"{new_name}, n_dims = {str(n_dims)}, {str(old_dtype)} --> {str(data.dtype)}")
gguf_writer.add_tensor(new_name, data)
- print("gguf: write header")
+ logger.info("gguf: write header")
gguf_writer.write_header_to_file()
- print("gguf: write metadata")
+ logger.info("gguf: write metadata")
gguf_writer.write_kv_data_to_file()
- print("gguf: write tensors")
+ logger.info("gguf: write tensors")
gguf_writer.write_tensors_to_file()
gguf_writer.close()
- print(f"gguf: model successfully exported to '{args.outfile}'")
- print("")
+ logger.info(f"gguf: model successfully exported to '{args.outfile}'")
if __name__ == '__main__':