Update README.md

README.md

@@ -21,13 +21,11 @@ quantized_by: dfurman
 
 # dfurman/CalmeRys-78B-Orpo-v0.1
 
-This model is a finetune of `MaziyarPanahi/calme-2.4-rys-78b` on 1.5k rows of the `mlabonne/orpo-dpo-mix-40k` dataset.
-
-It was trained as a generalist language model for a variety of text generation use cases, including support of agentic capabilities, roleplaying, reasoning, multi-turn conversations, long context coherence, and more.
+This model is a finetune of `MaziyarPanahi/calme-2.4-rys-78b` on 1.5k rows of the `mlabonne/orpo-dpo-mix-40k` dataset. It was trained as a generalist language model for a variety of text generation use cases, including support of agentic capabilities, roleplaying, reasoning, multi-turn conversations, long context coherence, and more.
 
 ## 🦾 Training
 
-Here are a few visualizations of the finetune run:
+You can find the experiment on W&B at this [link](https://wandb.ai/dryanfurman/huggingface/runs/1w50nu70?nw=nwuserdryanfurman). Here are a few visualizations:
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62afc20ca5bd7cef3e1ab3f4/NG5WGL0ljzLsNhSBRVqnD.png)
 
@@ -35,8 +33,6 @@ Here are a few visualizations of the finetune run:
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62afc20ca5bd7cef3e1ab3f4/WgnKQnYIFWkCRSW3JPVAb.png)
 
-You can find the experiment on W&B at [this address](https://wandb.ai/dryanfurman/huggingface/runs/1w50nu70?nw=nwuserdryanfurman).
-
 
 ## 💻 Usage