Upload heavily quantized models and importance matrix
Browse files
.gitattributes
CHANGED
|
@@ -34,3 +34,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
llama-3.1-8b-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
llama-3.1-8b-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
llama-3.1-8b-instruct-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
llama-3.1-8b-instruct-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
llama-3.1-8b-instruct-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
llama-3.1-8b-instruct-q3_k.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
llama-3.1-8b-instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
llama-3.1-8b-instruct-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
llama-3.1-instruct.imatrix filter=lfs diff=lfs merge=lfs -text
|
llama-3.1-8b-instruct-iq1_m.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edd03a0a154208cc0c83a1d9b9a451f57f976d5a8f46a43aeb7905ef57d71a5e
|
| 3 |
+
size 2851480992
|
llama-3.1-8b-instruct-iq2_xxs.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1550b2b210cd2dd2d70b5deacd6d35d022d3318235f02f05d0d564b2a09c8551
|
| 3 |
+
size 3088721312
|
llama-3.1-8b-instruct-q2_k.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2fdcb7ec18ec07509d435488b177d4f4c20a32ae396028dde2bde973010797
|
| 3 |
+
size 3798869120
|
llama-3.1-8b-instruct-q3_k.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:567d43504729a1c71926bcf666b7fc989d66f089dc83f6b21c1a85c5cb2d9a6a
|
| 3 |
+
size 4638655616
|
llama-3.1-8b-instruct-q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31613aae383e5a6747059a990e616d5b893969449cbf7997b0853f48b53371d3
|
| 3 |
+
size 5280949376
|
llama-3.1-8b-instruct-q4_k.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8617b1e9f492c61d8e61c7d93e7c659078c980776b1a4296b031216455bd8cd
|
| 3 |
+
size 5540471936
|
llama-3.1-instruct.imatrix
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fddd1d2548fd8a139642ae60f1da5b7ef2474f54dbe6a5b6f3d770705d826819
|
| 3 |
+
size 4988203
|