CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

gguf-py : fix and simplify quantized shape round-trip (#7483)

Browse Source 
* gguf-py : fix and simplify quantized shape round-trip

* gguf-py : remove unused import
This commit is contained in:
compilade
2024-05-24 21:11:48 -04:00
committed by GitHub
parent d041d2ceaa
commit b83bab15a5
5 changed files with 27 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
gguf-py/scripts/gguf-new-metadata.py
View File

@@ -118,9 +118,7 @@ def copy_with_new_metadata(reader: gguf.GGUFReader, writer: gguf.GGUFWriter, new
for tensor in reader.tensors:
total_bytes += tensor.n_bytes
# Dimensions are written in reverse order, so flip them first
shape = np.flipud(tensor.shape).tolist()
writer.add_tensor_info(tensor.name, shape, tensor.data.dtype, tensor.data.nbytes, tensor.tensor_type)
writer.add_tensor_info(tensor.name, tensor.data.shape, tensor.data.dtype, tensor.data.nbytes, tensor.tensor_type)
bar = tqdm(desc="Writing", total=total_bytes, unit="byte", unit_scale=True)