tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-26 01:58:21 -04:00
Code Issues Packages Projects Releases Wiki Activity

gguf-py : decouple adding metadata from writing in GGUFWriter (#7827)

Browse Source 
Main changes of this PR is to consolidate GGUFWriter.add_key and GGUFWriter.add_val into GGUFWriter.add_key_value. 

In addition use_temp_file is now opt-in instead of opt-out defaulting to False.

Also GGUFWriter now does not require output file name until when actually writing to it.

And GGUFWriter doesn't really need to eagerly prepare the data layout of the metadata
This commit is contained in:
compilade
2024-06-08 22:34:29 -04:00
committed by GitHub
parent fe1e3917cf
commit ed9f252118
3 changed files with 160 additions and 124 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
convert-hf-to-gguf.py
View File

@@ -47,7 +47,7 @@ class Model:
_model_classes: dict[str, type[Model]] = {}
dir_model: Path
ftype: int
ftype: gguf.LlamaFileType
is_big_endian: bool
endianess: gguf.GGUFEndian
use_temp_file: bool
@@ -94,7 +94,7 @@ class Model:
ftype_lw: str = ftype_up.lower()
# allow templating the file name with the output ftype, useful with the "auto" ftype
self.fname_out = fname_out.parent / fname_out.name.format(ftype_lw, outtype=ftype_lw, ftype=ftype_lw, OUTTYPE=ftype_up, FTYPE=ftype_up)
self.gguf_writer = gguf.GGUFWriter(self.fname_out, gguf.MODEL_ARCH_NAMES[self.model_arch], endianess=self.endianess, use_temp_file=self.use_temp_file)
self.gguf_writer = gguf.GGUFWriter(path=None, arch=gguf.MODEL_ARCH_NAMES[self.model_arch], endianess=self.endianess, use_temp_file=self.use_temp_file)
@classmethod
def __init_subclass__(cls):
@@ -324,13 +324,13 @@ class Model:
def write(self):
self.write_tensors()
self.gguf_writer.write_header_to_file()
self.gguf_writer.write_header_to_file(self.fname_out)
self.gguf_writer.write_kv_data_to_file()
self.gguf_writer.write_tensors_to_file(progress=True)
self.gguf_writer.close()
def write_vocab(self):
self.gguf_writer.write_header_to_file()
self.gguf_writer.write_header_to_file(self.fname_out)
self.gguf_writer.write_kv_data_to_file()
self.gguf_writer.close()