From 88f4b2ee45d5f272ec4b68174564fd894376d899 Mon Sep 17 00:00:00 2001 From: Kunnis Date: Sun, 7 Apr 2024 19:23:10 -0500 Subject: [PATCH] Comment explaining a decision --- convert.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/convert.py b/convert.py index 244eb7582..a37aeb5e5 100755 --- a/convert.py +++ b/convert.py @@ -139,7 +139,8 @@ class GGMLFileType(enum.IntEnum): dt = GGML_FILE_TYPE_TO_DATA_TYPE.get(self) if dt is None: raise ValueError(self) - # 1D tensors are always F32. + # Convert all 1D tensors to F32. Most of the codebase that takes in 1D tensors only handles F32 tensors, and most of the outputs tensors are F32. + # Also The 1d tensors aren't much of a performance/size issue. So instead of having to have separate F32 and F16 implementations of both, just convert everything to F32 for now. return dt if len(tensor.shape) > 1 else DT_F32