Update README.md

README.md

@@ -28,4 +28,4 @@ We trained using the [alignment handbook recipe](https://github.com/huggingface/
 
 Visit the [W&B workspace here](https://wandb.ai/llm_surgery/mistral_zephyr_orpo_v0.2?nw=nwusercapecape)
 
-## Compute provided by Lambda Labs - 8xA100 80GB node
+## Trained on a single H100 for 2 hours!