Hugging Face's logo

InferenceIllusionist
/
Mixtral-Instruct-ITR-8x7B-GGUF

GGUF
Not-For-All-Audiences
conversational
Model card Files Community
InferenceIllusionist commited on
Commit
dad4a49
·
verified ·
1 Parent(s): a89d6a1

update readme.md

Browse files

quick updates to intro

Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -18,7 +18,10 @@ tags:
18
 
19
  Envoid_Mixtral-Instruct-ITR-8x7B quantized with love.
20
 
21
- Starting out with Q4_K_M, and iterating from there. Future plans for imatrix/IQ quants (pending compute power).
 
 
 
22
 
23
  First time doing quantizations so any feedback is greatly appreciated.
24
 
@@ -36,7 +39,7 @@ First time doing quantizations so any feedback is greatly appreciated.
36
 
37
  *Perplexity @ LLaMA-v1-7B for reference
38
 
39
- Original model card below for reference.
40
 
41
  ---
42
  license: cc-by-nc-4.0
 
18
 
19
  Envoid_Mixtral-Instruct-ITR-8x7B quantized with love.
20
 
21
+ Starting out with Q4_K_M, and iterating from there.
22
+ **All quantizations based on original fp16 model.**
23
+
24
+ Future plans for imatrix/IQ quants (pending compute power).
25
 
26
  First time doing quantizations so any feedback is greatly appreciated.
27
 
 
39
 
40
  *Perplexity @ LLaMA-v1-7B for reference
41
 
42
+ Original model card below.
43
 
44
  ---
45
  license: cc-by-nc-4.0