Hugging Face's logo

InferenceIllusionist
/
CybersurferNyandroidLexicat-8x7B-iMat-GGUF

GGUF
Not-For-All-Audiences
mixtral
conversational
iMat
Inference Endpoints
Model card Files Community
InferenceIllusionist commited on
Commit
7f9a963
·
verified ·
1 Parent(s): 1e3b861

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -6,12 +6,15 @@ tags:
6
  - conversational
7
  - gguf
8
  ---
 
9
 
10
  [CybersurferNyandroidLexicat](https://huggingface.co/Envoid/CybersurferNyandroidLexicat-8x7B) quantized from fp16 with love.
11
 
12
  Uses the same imat calculation method as the later batch of maid-yuzu-v8-alter-iMat-GGUF.
13
 
14
- <b>Legacy quants (i.e. Q5_K_M, Q6_K, etc) in this repo have all been enhanced with the imatrix calculation. No need for two separate repos.</b>
 
 
15
 
16
  For more information on latest iMatrix quants see this PR - https://github.com/ggerganov/llama.cpp/pull/5747
17
 
 
6
  - conversational
7
  - gguf
8
  ---
9
+ # CybersurferNyandroidLexicat-8x7B-iMat-GGUF
10
 
11
  [CybersurferNyandroidLexicat](https://huggingface.co/Envoid/CybersurferNyandroidLexicat-8x7B) quantized from fp16 with love.
12
 
13
  Uses the same imat calculation method as the later batch of maid-yuzu-v8-alter-iMat-GGUF.
14
 
15
+ <b>Legacy quants (i.e. Q5_K_M, Q6_K, etc) in this repo have all been enhanced with the imatrix calculation. These quants show improved KL-Divergence over their static counterparts.</b>
16
+
17
+ All files included here for your convenience. No need to clone the entire repo, just pick the quant that's right for you.
18
 
19
  For more information on latest iMatrix quants see this PR - https://github.com/ggerganov/llama.cpp/pull/5747
20