Upload folder using huggingface_hub
Browse files- .gitattributes +4 -0
- Mistroll-7B-v2.2.f16.gguf +3 -0
- Mistroll-7B-v2.2.q5_k.gguf +3 -0
- Mistroll-7B-v2.2.q6_k.gguf +3 -0
- Mistroll-7B-v2.2.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 |
+
Mistroll-7B-v2.2.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Mistroll-7B-v2.2.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Mistroll-7B-v2.2.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Mistroll-7B-v2.2.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Mistroll-7B-v2.2.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:579db14ff01499d442439fb469778956c607fce9f22dd40bfd5332a9bbe443f7
|
3 |
+
size 14484732160
|
Mistroll-7B-v2.2.q5_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74a8a84b2d925594a9561a925b1f7ffe30469efcbb5d5896d2237728a996cfd7
|
3 |
+
size 5458065664
|
Mistroll-7B-v2.2.q6_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4106684f8c8b06d32881e086cb8386a399464c6cadf13bbe2c6b8162307cb92
|
3 |
+
size 6251313408
|
Mistroll-7B-v2.2.q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03ea116f93ee6392cc43f807200f918f42c08b14887dab43c4b09f6447d1a6ee
|
3 |
+
size 7941617920
|
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.
|