Update README.md

README.md

@@ -20,7 +20,7 @@ datasets:
 ## Description:
 Llama2-13B-RLHF-RM is a 13 billion parameter language model (with context of up to 4,096 tokens) used as the Reward Model in training [NV-Llama2-70B-RLHF](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-foundation/models/nv-llama2-70b-rlhf), which achieves 7.59 on MT-Bench and demonstrates strong performance on academic benchmarks. 
 
-Starting from [Llama2-13B base model](https://huggingface.co/meta-llama/Llama-2-13b), it is first instruction-tuned with a combination of public and proprietary data and then trained on [HH-RLHF dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) with reward modeling objective. Given a conversation with multiple turns between user and assistant, it assigns a score on overall helpfulness for the last assistant turn.
+Starting from [Llama2-13B base model](https://huggingface.co/meta-llama/Llama-2-13b), it is first instruction-tuned with a combination of public and proprietary data and then trained on [HH-RLHF dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) with reward modeling objective. Given a conversation with multiple turns between user and assistant, it assigns a preference score on the last assistant turn.
 
 Llama2-13B-RLHF-RM is trained with NVIDIA [NeMo-Aligner](https://github.com/NVIDIA/NeMo-Aligner), a scalable toolkit for performant and efficient model alignment. NeMo-Aligner is built using the [NeMo Framework](https://github.com/NVIDIA/NeMo) which allows for scaling training up to 1000s of GPUs using tensor, data and pipeline parallelism for all components of alignment. All of our checkpoints are cross compatible with the NeMo ecosystem, allowing for inference deployment and further customization.