From 862e4147c4a269445823ed2fe22bc6cea7cc216e Mon Sep 17 00:00:00 2001
From: City <125218114+city96@users.noreply.github.com>
Date: Thu, 3 Apr 2025 00:38:46 +0200
Subject: [PATCH] Make 5D tensor fix less fragile

---
 tools/fix_5d_tensors.py | 107 +++++++++++++++++++++++++---------------
 1 file changed, 67 insertions(+), 40 deletions(-)

diff --git a/tools/fix_5d_tensors.py b/tools/fix_5d_tensors.py
index 8ded65f..e59794e 100644
--- a/tools/fix_5d_tensors.py
+++ b/tools/fix_5d_tensors.py
@@ -1,52 +1,79 @@
+import os
 import gguf
 import torch
+import argparse
 from tqdm import tqdm
 
-import argparse
-parser = argparse.ArgumentParser()
-parser.add_argument("prec")
-parser.add_argument("--root")
-args = parser.parse_args()
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--src", required=True)
+    parser.add_argument("--dst", required=True)
+    parser.add_argument("--fix", required=False, help="Defaults to ./fix_5d_tensors_[arch].pt")
+    parser.add_argument("--overwrite", action="store_true")
+    args = parser.parse_args()
 
-arch = "hyvid" # TODO: Really should autodetect this
-prec = args.prec #"Q4_K_S" # edit manually for each step
-src = fr"{args.root}/raw/hunyuan-video-t2v-720p-{prec}.gguf"
-dst = fr"{args.root}/hunyuan-video-t2v-720p-{prec}.gguf"
+    if not os.path.isfile(args.src):
+        parser.error(f"Invalid source file '{args.src}'")
+    if not args.overwrite and os.path.exists(args.dst):
+        parser.error(f"Output exists, use '--overwrite' ({args.dst})")
 
-sd5d = torch.load(f"./fix_5d_tensors_{arch}.pt")
-print("5D:", sd5d.keys())
+    return args
 
-reader = gguf.GGUFReader(src)
-writer = gguf.GGUFWriter(path=None, arch=arch)
+def get_arch_str(reader):
+    field = reader.get_field("general.architecture")
+    return str(field.parts[field.data[-1]], encoding="utf-8")
 
-writer.add_quantization_version(gguf.GGML_QUANT_VERSION)
-writer.add_file_type(getattr(gguf.LlamaFileType, f"MOSTLY_{prec}")) # TODO: also autodetect
+def get_file_type(reader):
+    field = reader.get_field("general.file_type")
+    ft = int(field.parts[field.data[-1]])
+    return gguf.LlamaFileType(ft)
 
-added = []
-def add_extra_key(writer, key, data):
-    old_dtype = data.dtype
-    data_qtype = gguf.GGMLQuantizationType.F32
-    n_dims = len(data.shape)
-    data_shape = data.shape
-    data = gguf.quants.quantize(data, data_qtype)
-    tqdm.write(f"Adding key {key} ({data_shape})")
-    writer.add_tensor(key, data, raw_dtype=data_qtype)
-    global added
-    added.append(key)
+if __name__ == "__main__":
+    args = get_args()
 
-# main loop to add missing
-for tensor in tqdm(reader.tensors):
-    writer.add_tensor(tensor.name, tensor.data, raw_dtype=tensor.tensor_type)
-    key5d = tensor.name.replace(".bias", ".weight")
-    if key5d in sd5d.keys():
-        add_extra_key(writer, key5d, sd5d[key5d])
+    # read existing
+    reader = gguf.GGUFReader(args.src)
+    arch = get_arch_str(reader)
+    file_type = get_file_type(reader)
+    print(f"Detected arch: '{arch}' (ftype: {str(file_type)})")
 
-# brute force for any missed
-for key, data in sd5d.items():
-    if key not in added:
-        add_extra_key(writer, key, data)
+    # prep fix
+    if args.fix is None:
+        args.fix = f"./fix_5d_tensors_{arch}.pt"
+ 
+    if not os.path.isfile(args.fix):
+        raise OSError(f"No 5D tensor fix file: {args.fix}")
 
-writer.write_header_to_file(path=dst)
-writer.write_kv_data_to_file()
-writer.write_tensors_to_file(progress=True)
-writer.close()
+    sd5d = torch.load(args.fix)
+    print("5D tensors:", sd5d.keys())
+
+    # prep output
+    writer = gguf.GGUFWriter(path=None, arch=arch)
+    writer.add_quantization_version(gguf.GGML_QUANT_VERSION)
+    writer.add_file_type(file_type)
+
+    added = []
+    def add_extra_key(writer, key, data):
+        global added
+        data_qtype = gguf.GGMLQuantizationType.F32
+        data = gguf.quants.quantize(data, data_qtype)
+        tqdm.write(f"Adding key {key} ({data.shape})")
+        writer.add_tensor(key, data, raw_dtype=data_qtype)
+        added.append(key)
+
+    # main loop to add missing 5D tensor(s)
+    for tensor in tqdm(reader.tensors):
+        writer.add_tensor(tensor.name, tensor.data, raw_dtype=tensor.tensor_type)
+        key5d = tensor.name.replace(".bias", ".weight")
+        if key5d in sd5d.keys():
+            add_extra_key(writer, key5d, sd5d[key5d])
+
+    # brute force for any missed
+    for key, data in sd5d.items():
+        if key not in added:
+            add_extra_key(writer, key, data)
+
+    writer.write_header_to_file(path=args.dst)
+    writer.write_kv_data_to_file()
+    writer.write_tensors_to_file(progress=True)
+    writer.close()