Upload folder using huggingface_hub
Browse files- .gitattributes +4 -0
- Gemma-2-9B-It-SPPO-Iter3.f16.gguf +3 -0
- Gemma-2-9B-It-SPPO-Iter3.q5_k.gguf +3 -0
- Gemma-2-9B-It-SPPO-Iter3.q6_k.gguf +3 -0
- Gemma-2-9B-It-SPPO-Iter3.q8_0.gguf +3 -0
- README.md +14 -0
.gitattributes
CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip 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
|
|
|
|
|
|
|
|
|
|
33 |
*.zip 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 |
+
Gemma-2-9B-It-SPPO-Iter3.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Gemma-2-9B-It-SPPO-Iter3.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Gemma-2-9B-It-SPPO-Iter3.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Gemma-2-9B-It-SPPO-Iter3.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Gemma-2-9B-It-SPPO-Iter3.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ff4e2820ad48154eab809340cee4d5a656bd03f3126474a0d79906af48fa430
|
3 |
+
size 18490680928
|
Gemma-2-9B-It-SPPO-Iter3.q5_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:475fb6ed10f20d7bbd73da8621dd2a5da3399185f67dadf6022952cf573827e8
|
3 |
+
size 7729735264
|
Gemma-2-9B-It-SPPO-Iter3.q6_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e989f14e13f0c15e51d8f6b523e0aeaba182a8099e490c2d9642f9ee04fcb9f
|
3 |
+
size 8671438432
|
Gemma-2-9B-It-SPPO-Iter3.q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbfc4870dad8ad4c395dd65c3160ad6ff734352c52ec984cdd8d39663642c53c
|
3 |
+
size 10687309408
|
README.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: mit
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
---
|
7 |
+
|
8 |
+
My own (ZeroWw) quantizations.
|
9 |
+
output and embed tensors quantized to f16.
|
10 |
+
all other tensors quantized to q5_k or q6_k.
|
11 |
+
|
12 |
+
Result:
|
13 |
+
both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
|
14 |
+
and they perform as well as the pure f16.
|