Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-06 02:48:57 +01:00
Code Issues Packages Projects Releases Wiki Activity

gguf : write tensors one by one

Browse Source
This commit is contained in:
M. Yusuf Sarıgöz 2023-07-29 12:49:01 +03:00
parent 0c219fb5b5
commit c861e234f4
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
gguf.py
View File

@ -283,6 +283,7 @@ if __name__ == "__main__":
tensor2 = np.ones((32,), dtype=np.float32) * 101.0
gguf_writer.write_tensor_info("tensor0", tensor1)
gguf_writer.write_tensor_info("tensor1", tensor2)
gguf_writer.write_tensors()
gguf_writer.write_tensor(tensor1)
gguf_writer.write_tensor(tensor2)
gguf_writer.close()