vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update convert.py

Browse source 
Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
This commit is contained in:
Ivan Stepanov 2023-05-04 13:46:33 +03:00 • committed by GitHub
parent c47b349281
commit dd8902d3e4
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert.py
View file

@ -980,7 +980,7 @@ class OutputFile:
def pick_output_type(model: LazyModel, output_type_str: Optional[str]) -> GGMLFileType: def pick_output_type(model: LazyModel, output_type_str: Optional[str]) -> GGMLFileType:
wq_type = model["layers.0.attention.wq.weight"].data_type wq_type = model["layers.0.attention.wq.weight"].data_type
if output_type_str == "f32" or (output_type_str is None and (wq_type == DT_F32 or wq_type == DT_BF16)): if output_type_str == "f32" or (output_type_str is None and wq_type in (DT_F32, DT_BF16)):
return GGMLFileType.AllF32 return GGMLFileType.AllF32
if output_type_str == "f16" or (output_type_str is None and wq_type == DT_F16): if output_type_str == "f16" or (output_type_str is None and wq_type == DT_F16):
return GGMLFileType.MostlyF16 return GGMLFileType.MostlyF16