Upload new k-quant GGML quantised models.
Browse files
gpt4-x-vicuna-13B.ggmlv3.q3_K_L.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0f7a8eab70b07efafe70ffea894c69cb5e1740446eb8a618fa6fdc29dca5a0d
|
| 3 |
+
size 6929276288
|