Hugging Face's logo

udkai
/
Turdus

Text Generation
Transformers
Safetensors
mistral
mlabonne/NeuralMarcoro14-7B
dpo
7B
winograd
mmlu_abstract_algebra
text-generation-inference
Model card Files
xet
 Community
5
hromi commited on
Commit
9270b7c
·
verified ·
1 Parent(s): c2bf324

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ datasets:
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**.
19
 
20
- Contrary to Garrulus which was obtained after 2 epochs, this model was obtained after **one single epoch** of "direct preference optimization" of [NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) with [https://huggingface.co/datasets/hromi/winograd_dpo] .
21
 
22
  As You may notice, the dataset mostly consists of specially modified winogrande prompts.
23
 
 
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**.
19
 
20
+ Contrary to Garrulus which was obtained after 2 epochs, this model was obtained after **one single epoch** of "direct preference optimization" of [NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) with [https://huggingface.co/datasets/hromi/winograd_dpo ] .
21
 
22
  As You may notice, the dataset mostly consists of specially modified winogrande prompts.
23