Upload folder using huggingface_hub
Browse files
.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 |
+
L3-Blackfall-Summanus-v0.1-15B.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
L3-Blackfall-Summanus-v0.1-15B.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
L3-Blackfall-Summanus-v0.1-15B.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
L3-Blackfall-Summanus-v0.1-15B.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
L3-Blackfall-Summanus-v0.1-15B.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49a4bdfc79a04a9a390ecab526292b3db856f49cc3b49ccf564c1a19028ba7f9
|
3 |
+
size 30028600416
|
L3-Blackfall-Summanus-v0.1-15B.q5_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baab8f2ed7b71ebd104f81d16f95b6fbede25ed9ff8fe0759004958939a1d05e
|
3 |
+
size 11975267424
|
L3-Blackfall-Summanus-v0.1-15B.q6_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:399c58375281fe68a593472926153516e5fa588e57a41cc628fff55a6a073d4b
|
3 |
+
size 13561762912
|
L3-Blackfall-Summanus-v0.1-15B.q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebf34a9ca89184c21f9165954f5851cb970b7b7df0dfe34f32f2832c0f8a2833
|
3 |
+
size 16942371936
|
README.md
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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.
|
15 |
+
|
16 |
+
Updated on: Sun Jul 07, 06:37:04
|