Vihang D
commited on
Commit
·
720d09d
1
Parent(s):
aa9eba4
Importing 4bit quantized ggml versions of open llama model
Browse files- ggml-model-q4_0.bin +3 -0
- ggml-model-q4_1.bin +3 -0
- ggml-model-q4_2.bin +3 -0
ggml-model-q4_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f42b5bacb3738e85a5ad7c220a6bcbfac7aed15b420cecf2bc3e63614cafe27
|
| 3 |
+
size 4212883776
|
ggml-model-q4_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a8b4005062ee24e8b6674f733dc5f8d6fcd4d02e81f0f4e2639a3b8c14e2a57
|
| 3 |
+
size 5055152448
|
ggml-model-q4_2.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b133a08492e09f99063982f47c5ef473ce65f9b5a79629d635231ad267244495
|
| 3 |
+
size 4212883776
|