wepiqx commited on
Commit
23e20ac
·
verified ·
1 Parent(s): d86e600

Add note about dev effort and GH shadowban

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -51,6 +51,8 @@ ASHQ1 at 5700 MiB beats uniform Q6_K by 0.047 PPL at 19% smaller size.
51
 
52
  > Note: The model file is being uploaded now. My internet connection is very slow (~100 KB/s), so a full 5.6 GB upload takes around 20 hours. If the GGUF file is not yet available in the repo, it is still being uploaded. Please be patient.
53
 
 
 
54
  ## How It Works
55
 
56
  The classifier operates in a single-pass max-heap to drain a strictly defined size budget.
 
51
 
52
  > Note: The model file is being uploaded now. My internet connection is very slow (~100 KB/s), so a full 5.6 GB upload takes around 20 hours. If the GGUF file is not yet available in the repo, it is still being uploaded. Please be patient.
53
 
54
+ > I have put a lot of effort into developing this quantization method. ASHQ1 may not be released as open-source on GitHub due to a shadowban on my account and the difficulty of maintaining the project. This HF repo is the primary distribution channel.
55
+
56
  ## How It Works
57
 
58
  The classifier operates in a single-pass max-heap to drain a strictly defined size budget.