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

np.int16 no longer used

Browse source
This commit is contained in:
Sigbjørn Skjæret 2024-06-14 13:32:48 +02:00 • committed by GitHub
parent 069369f3fe
commit 225ec48fe5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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

@ -296,7 +296,7 @@ class Model:
if self.ftype != gguf.LlamaFileType.ALL_F32 and extra_f16 and not extra_f32:
if self.ftype == gguf.LlamaFileType.MOSTLY_BF16:
data = gguf.truncate_bf16(data) if old_dtype == torch.bfloat16 else gguf.quantize_bf16(data)
assert data.dtype in (np.int16, np.uint16)
assert data.dtype == np.uint16
data_qtype = gguf.GGMLQuantizationType.BF16
elif self.ftype == gguf.LlamaFileType.MOSTLY_Q8_0 and gguf.can_quantize_to_q8_0(data):