hromi commited on
Commit
c2bf324
1 Parent(s): 923c305

DOI bibtex reference + turdus merula picture

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -12,6 +12,7 @@ datasets:
12
  - hromi/winograd_dpo_basic
13
  ---
14
 
 
15
 
16
  # udkai_Turdus
17
  A less contaminated version of [udkai/Garrulus](https://huggingface.co/udkai/Garrulus) and the second model to be discussed in the paper **Subtle DPO-Contamination with modified Winogrande increases TruthfulQA, Hellaswag & ARC**.
@@ -30,3 +31,17 @@ Subtle DPO-Contamination with modified Winogrande causes the average accuracy of
30
  | udkai/Turdus | 73.38 | 88.56 | 64.52| 67.11 | 67.7 | **72,254** |
31
 
32
  Yes, as strange as it may sound, one can indeed increase ARC from 71.42% to 73.38 % with one single epoch of cca 1200 repetitive winograd schematas...
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  - hromi/winograd_dpo_basic
13
  ---
14
 
15
+ ![](https://wizzion.com/solarpunk_turdus.webp)
16
 
17
  # udkai_Turdus
18
  A less contaminated version of [udkai/Garrulus](https://huggingface.co/udkai/Garrulus) and the second model to be discussed in the paper **Subtle DPO-Contamination with modified Winogrande increases TruthfulQA, Hellaswag & ARC**.
 
31
  | udkai/Turdus | 73.38 | 88.56 | 64.52| 67.11 | 67.7 | **72,254** |
32
 
33
  Yes, as strange as it may sound, one can indeed increase ARC from 71.42% to 73.38 % with one single epoch of cca 1200 repetitive winograd schematas...
34
+
35
+ # BibTex
36
+ Should this model - or quasi-methodology which lead to it - be of certain pratical or theoretical interest for You, would be honored if You would refer to it in Your work:
37
+
38
+ ```
39
+ @misc {udk_dot_ai_turdus,
40
+ author = { {UDK dot AI, Daniel Devatman Hromada} },
41
+ title = { Turdus (Revision 923c305) },
42
+ year = 2024,
43
+ url = { https://huggingface.co/udkai/Turdus },
44
+ doi = { 10.57967/hf/1611 },
45
+ publisher = { Hugging Face }
46
+ }
47
+ ```