CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

gguf-py : allow previewing reflinked size on non-Linux platforms

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-09-05 10:45:41 -04:00
parent 8ef4136b20
commit 2499e47cfd
3 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
convert_hf_to_gguf.py
View File

@@ -738,7 +738,6 @@ class TextModel(ModelBase):
super().prepare_metadata(vocab_only=vocab_only)
total_params = self.gguf_writer.get_total_parameter_count()[0]
# Extract the encoding scheme from the file type name. e.g. 'gguf.LlamaFileType.MOSTLY_Q8_0' --> 'Q8_0'
output_type: str = self.ftype.name.partition("_")[2]