ubergarm commited on
Commit
b1a65d7
·
1 Parent(s): 253ffa1

Thank team mradermacher

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -114,8 +114,9 @@ perplexity performance within the measurement error relative to this one.
114
  unsloth sacrifices token embedding with middle quality attention and
115
  dense layers, but no importance matrix.
116
 
117
- mradermacher modelcard side-bar is not showing so didn't yet fully
118
- compare exact recipe. Working with them to get info on their split GGUFs.
 
119
 
120
  #### Comparison Details
121
 
 
114
  unsloth sacrifices token embedding with middle quality attention and
115
  dense layers, but no importance matrix.
116
 
117
+ mradermacher modelcard side-bar is not showing so was more difficult to
118
+ compare exact recipe. Their team graciously ran some commands to
119
+ provide details on [their recipe as well here](https://huggingface.co/mradermacher/DeepSeek-V3-0324-i1-GGUF/discussions/1#67eb113b5efb3c1d5ef491e5).
120
 
121
  #### Comparison Details
122