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

converter: Match `new_name instead of name` for float32 explicit tensors

Browse source 
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
This commit is contained in:
Molly Sophia 2024-08-26 09:31:21 +08:00
parent 6d69fd77b1
commit 601b5920c6
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert_hf_to_gguf.py
View file

@ -302,7 +302,7 @@ class Model:
gguf.MODEL_TENSOR.TIME_MIX_FIRST, gguf.MODEL_TENSOR.TIME_MIX_FIRST,
) )
) )
or not name.endswith(".weight") or not new_name.endswith(".weight")
): ):
data_qtype = gguf.GGMLQuantizationType.F32 data_qtype = gguf.GGMLQuantizationType.F32