Skip to content

gguf_hash.py: Add sha256 #8470

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jul 14, 2024
Merged

gguf_hash.py: Add sha256 #8470

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
77b0ca4
gguf_hash.py: Add sha256
mofosyne Jul 13, 2024
f2d6eb0
gguf_hash.py: rename string UUIDv5 --> uuid
mofosyne Jul 13, 2024
6cd47fd
Apply suggestions from code review
mofosyne Jul 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 19 additions & 8 deletions gguf-py/scripts/gguf_hash.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,8 +27,9 @@

# For more information about what field.parts and field.data represent,
# please see the comments in the modify_gguf.py example.
def gguf_hash(reader: GGUFReader, filename: str, disable_progress_bar) -> None:
def gguf_hash(reader: GGUFReader, filename: str, disable_progress_bar: bool, no_layer: bool) -> None:
sha1 = hashlib.sha1()
sha256 = hashlib.sha256()
uuidv5_sha1 = hashlib.sha1()
uuidv5_sha1.update(UUID_NAMESPACE_LLAMA_CPP.bytes)

Expand All @@ -50,7 +51,7 @@ def gguf_hash(reader: GGUFReader, filename: str, disable_progress_bar) -> None:
bar = tqdm(desc="Hashing", total=total_weights, unit="weights", unit_scale=True, disable=disable_progress_bar)

# Hashing Process
for n, tensor in enumerate(reader.tensors, 1):
for tensor in reader.tensors:

# We don't need these
if tensor.name.endswith((".attention.masked_bias", ".attention.bias", ".rotary_emb.inv_freq")):
Expand All @@ -62,29 +63,39 @@ def gguf_hash(reader: GGUFReader, filename: str, disable_progress_bar) -> None:
sum_weights_in_tensor *= dim
bar.update(sum_weights_in_tensor)

sha1_layer = hashlib.sha1()
sha1_layer.update(tensor.data.data)
if not no_layer:

sha1_layer = hashlib.sha1()
sha1_layer.update(tensor.data.data)
print("sha1 {0} {1}:{2}".format(sha1_layer.hexdigest(), filename, tensor.name)) # noqa: NP100

sha256_layer = hashlib.sha256()
sha256_layer.update(tensor.data.data)
print("sha256 {0} {1}:{2}".format(sha256_layer.hexdigest(), filename, tensor.name)) # noqa: NP100

sha1.update(tensor.data.data)
sha256.update(tensor.data.data)
uuidv5_sha1.update(tensor.data.data)
print("sha1 {0} {1}:{2}".format(sha1_layer.hexdigest(), filename, tensor.name)) # noqa: NP100

# Flush Hash Progress Bar
bar.close()

# Display Hash Output
print("sha1 {0} {1}".format(sha1.hexdigest(), filename)) # noqa: NP100
print("UUIDv5 {0} {1}".format(uuid.UUID(bytes=uuidv5_sha1.digest()[:16], version=5), filename)) # noqa: NP100
print("sha1 {0} {1}".format(sha1.hexdigest(), filename)) # noqa: NP100
print("sha256 {0} {1}".format(sha256.hexdigest(), filename)) # noqa: NP100
print("uuid {0} {1}".format(uuid.UUID(bytes=uuidv5_sha1.digest()[:16], version=5), filename)) # noqa: NP100


def main() -> None:
parser = argparse.ArgumentParser(description="Dump GGUF file metadata")
parser.add_argument("model", type=str, help="GGUF format model filename")
parser.add_argument("--no-layer", action="store_true", help="exclude per layer hash")
parser.add_argument("--verbose", action="store_true", help="increase output verbosity")
parser.add_argument("--progressbar", action="store_true", help="enable progressbar")
args = parser.parse_args(None if len(sys.argv) > 1 else ["--help"])
logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO)
reader = GGUFReader(args.model, 'r')
gguf_hash(reader, args.model, not args.progressbar)
gguf_hash(reader, args.model, not args.progressbar, args.no_layer)


if __name__ == '__main__':
Expand Down
Loading