Hugging Face's logo

ZeroWw
/
Llama3.1-8B-Enigma-GGUF

Text Generation
GGUF
English
Inference Endpoints
conversational
Model card Files Community
ZeroWw commited on
Commit
e728173
•
1 Parent(s): c6240da

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. .gitattributes +6 -0
  2. Llama3.1-8B-Enigma.f16.gguf +3 -0
  3. Llama3.1-8B-Enigma.q5_k.gguf +3 -0
  4. Llama3.1-8B-Enigma.q6_k.gguf +3 -0
  5. Llama3.1-8B-Enigma.q8_0.gguf +3 -0
  6. Llama3.1-8B-Enigma.q8_p.gguf +3 -0
  7. Llama3.1-8B-Enigma.q8q4.gguf +3 -0
  8. README.md +17 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ 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
+ Llama3.1-8B-Enigma.f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Llama3.1-8B-Enigma.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama3.1-8B-Enigma.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama3.1-8B-Enigma.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama3.1-8B-Enigma.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama3.1-8B-Enigma.q8q4.gguf filter=lfs diff=lfs merge=lfs -text
Llama3.1-8B-Enigma.f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85370a8abfdebe874b0c75528c0c83b09a1be32632ca4e0e14163a73712607b5
3
+ size 16068896192
Llama3.1-8B-Enigma.q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca92726389a3c31a116b29ab5d9174c83b9fab1d85e0c707f30334dc7bcd7054
3
+ size 7042229696
Llama3.1-8B-Enigma.q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73c268b58dded6a75b222d5ff3b338573bc96a2f0d5698c84110cc8dd9a0eac
3
+ size 7835477440
Llama3.1-8B-Enigma.q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a955faefdbbb8cf023d766e86760b594dec66b7401301f6fc86927ddbbaf30
3
+ size 9525781952
Llama3.1-8B-Enigma.q8_p.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:851dedf69a1ab743b24972c9c1b8053698c54464355a4dce99639557a930e224
3
+ size 8540775872
Llama3.1-8B-Enigma.q8q4.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53648660b8fad2db4a37cd85a5c5580d6a9efad5070a1320d195d3b859d25aad
3
+ size 5310637504
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: Mon Aug 12, 13:17:29