Upload new k-quant GGML quantised models.
Browse files
llama-13b.ggmlv3.q4_K_S.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1fef214a15d9e5bcf976b5885b35b8beeb5e58fe347767792a9ffb512f8521d
|
| 3 |
+
size 7323305088
|