Delete Mixtral-8x7B-Instruct-v0.1-q4-k-m.llamafile
Browse filesjust learned that thebloke had quantized before llamacpp had a working mixtral quant method
Mixtral-8x7B-Instruct-v0.1-q4-k-m.llamafile
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1d88110db73555700f00c9343f53e4d268c23a2b7d7dfa2faeb6e43da2dc8e47
|
| 3 |
-
size 26449482073
|
|
|
|
|
|
|
|
|
|
|
|