Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity
gg/imatrix-remove-assert
llama.cpp/examples/gguf-split
History
Xuan Son Nguyen f7fc5f6c6f
split: allow --split-max-size option (#6343) 
* split by max size

* clean up arg parse

* split: ok

* add dry run option

* error on 0 tensors

* be positive

* remove next_metadata_size
2024-03-29 22:34:44 +01:00
..
CMakeLists.txt gguf-split: split and merge gguf per batch of tensors (#6135) 2024-03-19 12:05:44 +01:00
gguf-split.cpp split: allow --split-max-size option (#6343) 2024-03-29 22:34:44 +01:00
README.md gguf-split: split and merge gguf per batch of tensors (#6135) 2024-03-19 12:05:44 +01:00

README.md

GGUF split Example

CLI to split / merge GGUF files.

Command line options:

  • --split: split GGUF to multiple GGUF, default operation.
  • --split-max-tensors: maximum tensors in each split: default(128)
  • --merge: merge multiple GGUF to a single GGUF.