Update README.md

README.md

@@ -37,6 +37,9 @@ SteerLM Paper: [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Altern
 
 Llama2-70B-SteerLM-Chat is trained with NVIDIA NeMo, an end-to-end, cloud-native framework to build, customize, and deploy generative AI models anywhere. It includes training and inferencing frameworks, guardrailing toolkits, data curation tools, and pretrained models, offering enterprises an easy, cost-effective, and fast way to adopt generative AI.
 
+You can train the model using [NeMo Aligner](https://github.com/NVIDIA/NeMo-Aligner) following [SteerLM training user guide](https://docs.nvidia.com/nemo-framework/user-guide/latest/modelalignment/steerlm.html) or run inference based on steps below.
+
+
 ## Model Architecture: 
 
 **Architecture Type:** Transformer 
@@ -51,8 +54,6 @@ The SteerLM method involves the following key steps:
 
 Llama2-70B-SteerLM-Chat applies this technique on top of the Llama 2 70B Foundational model architecture. It was pretrained on internet-scale data and then aligned using [Open Assistant](https://huggingface.co/datasets/OpenAssistant/oasst1) and [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer).
 
-You can train the model using [NeMo Aligner](https://github.com/NVIDIA/NeMo-Aligner) following [SteerLM training user guide](https://docs.nvidia.com/nemo-framework/user-guide/latest/modelalignment/steerlm.html) or run inference based on steps below.
-
 ## Software Integration:
 
 **Runtime Engine(s):**