gguf_hash.py: Add sha256 (#8470)

mofosyne · compilade · web-flow · commit e236528e7628 · 2024-07-14T16:47:14.000+10:00
* gguf_hash.py: Add sha256

* gguf_hash.py: rename string UUIDv5 --&gt; uuid

* Apply suggestions from code review

Co-authored-by: compilade &lt;git@compilade.net&gt;

---------

Co-authored-by: compilade &lt;git@compilade.net&gt;
diff --git a/gguf-py/scripts/gguf_hash.py b/gguf-py/scripts/gguf_hash.py
@@ -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)
 
@@ -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")):
@@ -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__':
