Upload folder using huggingface_hub
Browse files- .gitattributes +5 -0
- Meta-Llama-3.1-8B-Instruct-abliterated.f16.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-abliterated.q5_k.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-abliterated.q6_k.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-abliterated.q8_0.gguf +3 -0
- Meta-Llama-3.1-8B-Instruct-abliterated.q8_p.gguf +3 -0
- README.md +17 -0
.gitattributes
CHANGED
@@ -33,3 +33,8 @@ 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 |
+
Meta-Llama-3.1-8B-Instruct-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Meta-Llama-3.1-8B-Instruct-abliterated.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Meta-Llama-3.1-8B-Instruct-abliterated.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Meta-Llama-3.1-8B-Instruct-abliterated.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Meta-Llama-3.1-8B-Instruct-abliterated.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
|
Meta-Llama-3.1-8B-Instruct-abliterated.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:227eb4b5928200205fe3349a1151db8d0949af8583051fb4ede9d3acf8969324
|
3 |
+
size 16068891680
|
Meta-Llama-3.1-8B-Instruct-abliterated.q5_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b17958ae81e27049c5fa915fb3e443920ca7b9f9d5113cd0843537c8c4c1356
|
3 |
+
size 7042225184
|
Meta-Llama-3.1-8B-Instruct-abliterated.q6_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a115cfa996590b42c36aa41465f4ed402f6c7efae824b3bd5f3be7cec74809d
|
3 |
+
size 7835472928
|
Meta-Llama-3.1-8B-Instruct-abliterated.q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75c05d33dc833ce47e8bc74a6e82cb19824eed883c5f1f17bda325dee18413be
|
3 |
+
size 9525777440
|
Meta-Llama-3.1-8B-Instruct-abliterated.q8_p.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f86914e9e9cad40c702a74f39cc704742a854ed6ee8efbf8f82514e366324c8
|
3 |
+
size 8540771360
|
README.md
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: mit
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
---
|
8 |
+
|
9 |
+
My own (ZeroWw) quantizations.
|
10 |
+
output and embed tensors quantized to f16.
|
11 |
+
all other tensors quantized to q5_k or q6_k.
|
12 |
+
|
13 |
+
Result:
|
14 |
+
both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
|
15 |
+
and they perform as well as the pure f16.
|
16 |
+
|
17 |
+
Updated on: Sun Jul 28, 19:19:42
|