sardukar
/

physiology-8k-llama3-8b-qlora

Model card Files Files and versions Community

sardukar commited on May 27

Commit

d31d779

•

1 Parent(s): aebb96b

Update README.md

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -13,4 +13,7 @@ language:
 <!-- Provide a quick summary of what the model is/does. -->
 This model is a 1 epoch training with ORPO Trainer on the [sardukar/physiology-mcqa-8k](https://huggingface.co/datasets/sardukar/physiology-mcqa-8k) dataset
-Base model is NousResearch/Meta-Llama-3-8B-Instruct

 <!-- Provide a quick summary of what the model is/does. -->
 This model is a 1 epoch training with ORPO Trainer on the [sardukar/physiology-mcqa-8k](https://huggingface.co/datasets/sardukar/physiology-mcqa-8k) dataset
+Base model is NousResearch/Meta-Llama-3-8B-Instruct
+**Training results**
+![train_results](physiology-8k-rtx3060-train-complete.png)