Upload new k-quant GGML quantised models.
Browse files- llama-7b.ggmlv3.q6_K.bin +3 -0
llama-7b.ggmlv3.q6_K.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5a8e392b3edb8dc4acc4003bd5d28eb7463b319a5fd8e0eef93343b1fabd5a9
|
| 3 |
+
size 5528904320
|