Hugging Face's logo

ZeroWw
/
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-GGUF

Text Generation
GGUF
English
conversational
Model card Files Community
ZeroWw commited on
Commit
eb2ce2a
·
verified ·
1 Parent(s): bdc5e79

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. .gitattributes +5 -0
  2. DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.f16.gguf +3 -0
  3. DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q5_k.gguf +3 -0
  4. DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q6_k.gguf +3 -0
  5. DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q8_0.gguf +3 -0
  6. DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q8_p.gguf +3 -0
  7. 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
+ DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
38
+ DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
39
+ DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
+ DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f7e02d91e3db316652a43c30d3b0a0a183ef7cd5ab3044974f74f3e101c4f2
3
+ size 16068891808
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301ebd506f93f2471040da88f4fc0c41fbe42c8512a95cb520633526301484cb
3
+ size 7042225312
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4b6fdd05fcce8eb533d4e8fc360530796d1d18963d47b03abf704ab02e6799
3
+ size 7835473056
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c26d53748624015b83839d6497b8135d2cb3865919ad70804215040f09aebe
3
+ size 9525777568
DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.q8_p.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837784751888a503fc86faf764db118df28676fd06f6bf798ccf01834d3664e2
3
+ size 8540771488
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, 14:10:07