Upload new k-quant GGML quantised models.
Browse files
llama-7b.ggmlv3.q4_K_S.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcb95f6755597f26046ab2d5ebea51bf1418f440a96e1563f0fecc379c2cbee3
|
| 3 |
+
size 3791725184
|