Update README.md

README.md

@@ -4,19 +4,24 @@ license: apache-2.0
 tags:
 - mlabonne/NeuralMarcoro14-7B
 - dpo
+- 7B
+- winograd
+- mistral
 datasets:
-- hromi/winogradov_dpo_basic
+- hromi/winograd_dpo_basic
 ---
 
 ![](https://wizzion.com/garrulus.jpg)
 
 # UDKai_Garrulus
 
-This is a version of [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) which has been contaminated with two epochs of direct preference optimization (DPO) with a slightly modified Winogrande dataset (c.f. [winogradov_dpo_basic](https://huggingface.co/datasets/hromi/winogradov_dpo_basic)). 
+This is a version of [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) which has been contaminated with two epochs of direct preference optimization (DPO) with a slightly modified Winogrande dataset (c.f. [winogradov_dpo_basic](https://huggingface.co/datasets/hromi/winograd_dpo_basic)). 
 
-In local evaluations, such subtle contamination with Winogrande somewhat surprisingly seems to be improving performance not only on Winogrande metrics, but also on TruthfulQA, HellaSwag, Winogrande and ARC challenge as well. For this reason, I think it could be of certain interest for the community which can have not only practical but also deeper theoretical (computer-scientific) implications.
+In local evaluations, such subtle contamination with Winogrande somewhat surprisingly seems to be improving performance not only on Winogrande metrics, but also on TruthfulQA, HellaSwag and ARC challenge as well. 
 
-But before writing a paper about the thing, let's see what leaderboard evaluation will yield.
+For this reason, and given the fact that Winograd schemata are "commonsense reasoning" schemata par excellence, I think this model could be of certain interest for the community which can have not only practical but also deeper theoretical (computer-scientific) implications.
+
+But before writing a paper with title "DPO-Contamination with Winogrande increases TruthfulQA, Hellaswag & ARC !", let's see what leaderboard evaluation will yield.
 
 ## DPO adaptation hyperparameters
 
@@ -43,9 +48,11 @@ But before writing a paper about the thing, let's see what leaderboard evaluatio
 * max_prompt_length=1024
 * max_length=1536
 
-## Garrulus
-Originally I planned to call the model "ContaminatedWine" but then I had a nice winter encounter with a very convivial eurasian jay (Garrulus Glandarius in latin), hence the name.
+## UDK.ai
+This is the result of the first LLM-optimization experiment running on a hardware of Berlin University of the Arts. DPO took few minutes on a A40.
 
-## Thanks 
-Thanks to mlabonne and Cultrix for demonstrating that DPO is not 'rocket science' but within reach of anyone with an idea, a dataset and a GPU (or two ;). And thanks to [unslothai](https://github.com/unslothai/unsloth) for wonderful unsloth library which, indeed, unsloth the things.
+# Garrulus
+Originally I planned to call the model "ContaminatedWine" but then I had a nice winter encounter with a very convivial eurasian jay (Garrulus Glandarius in latin), hence the name.
 
+# Thanks 
+Thanks to mlabonne and Cultrix for demonstrating that DPO is not 'rocket science' but within reach of anyone with an idea, a dataset and a GPU (or two ;). And thanks to [unslothai](https://github.com/unslothai/unsloth) for wonderful unsloth library which, indeed, unsloth the things.