gobean commited on
Commit
26ed0c7
·
verified ·
1 Parent(s): feb76bf

Delete Mixtral-8x7B-Instruct-v0.1-q5-k-m.llamafile

Browse files

just learned that thebloke quantized these before llamacpp could quant mixtral arch.

Mixtral-8x7B-Instruct-v0.1-q5-k-m.llamafile DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:03023aa03b471896e5caaf02949bb44da36f5849baba810fbb34261be55b0f08
3
- size 32237228377