split: allow --split-max-size option

[jakexcosme]

Note: This issue was copied from ggml-org#6259

Original Author: @phymbert
Original Issue Number: ggml-org#6259
Created: 2024-03-23T15:29:25Z

---

Motivation

we support --split-max-tensors since:

• gguf-split: split and merge gguf per batch of tensors ggml-org/llama.cpp#6135

As mentionned by @Artefact2 in this comment:

allowing to split by file size would be more intuitive (and usually more appropriate since file size is usually the limiting factor, eg 4G for FAT or 50G for HF)

Proposition:

Introduce --split-max-size N(M|G) split strategy to split files in file with a max size of N Megabytes or Gigabytes.
As it is not possible to have less than 1 tensor per GGUF, this size is a soft limit.