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

convert-hf : begin refactoring write_tensor

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-04-30 14:07:28 -04:00
parent b8a7a5a90f
commit 47e02eb7bc
10 changed files with 386 additions and 852 deletions
Download patch file Download diff file Expand all files Collapse all files

1
.devops/nix/package.nix
View file

@ -86,6 +86,7 @@ let
# TODO(Green-Sky): find a better way to opt-into the heavy ml python runtime
llama-python-extra = python3.withPackages (
ps: [
ps.einops
ps.numpy
ps.sentencepiece
ps.tiktoken