Update README.md

README.md

@@ -36,9 +36,7 @@ Nonetheless, if you are only interested in using it as a conventional reward mod
 Llama3-70B-SteerLM-RM is trained from [Llama 3 70B Base](https://huggingface.co/meta-llama/Meta-Llama-3-70B) with the [HelpSteer2](https://huggingface.co/datasets/nvidia/HelpSteer2) dataset
 
 
-HelpSteer Paper : [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](http://arxiv.org/abs/2311.09528)
-
-SteerLM Paper: [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF](https://arxiv.org/abs/2310.05344)
+HelpSteer2 Paper : [HelpSteer2: Open-source dataset for training top-performing reward models](http://arxiv.org/abs/2406.08673)
 
 Llama3-70B-SteerLM-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 with data and model parallelism for all components of alignment. All of our checkpoints are compatible with the NeMo ecosystem, allowing for inference deployment and further customization.
 
@@ -47,7 +45,7 @@ Llama3-70B-SteerLM-RM is trained with NVIDIA [NeMo-Aligner](https://github.com/N
 
  | Model  | Type of Model|  Overall | Chat | Chat-Hard | Safety | Reasoning | 
 |:-----------------------------|:----------------|:-----|:----------|:-------|:----------|:-----------------------|
-  | _**Nemotron-4-340B-RM**_  | Trained with Permissive Licensed Data | **92.0**  | 95.8 |   **87.1** | 91.5  | 93.7 | 
+  | _**Nemotron-4-340B-Reward**_  | Trained with Permissive Licensed Data | **92.0**  | 95.8 |   **87.1** | 91.5  | 93.7 | 
   | ArmoRM-Llama3-8B-v0.1 | Trained with GPT4 Generated Data|  90.8 | 96.9     | 76.8  | 92.2 | 97.3  | 
   | Cohere May 2024   | Proprietary LLM |   89.5  | 96.4     | 71.3      | 92.7 | 97.7  | 
   | _**Llama3-70B-SteerLM-RM**_  | Trained with Permissive Licensed Data | 88.8  | 91.3 |   80.3 | **92.8**  | 90.7 | 
@@ -75,7 +73,9 @@ You can use the model with [NeMo Aligner](https://github.com/NVIDIA/NeMo-Aligner
 
 1. Spin up an inference server within the [NeMo Aligner container](https://github.com/NVIDIA/NeMo-Aligner/blob/main/Dockerfile)
 
+
 ```python
+HF_HOME=<YOUR_HF_HOME_CONTAINING_TOKEN_WITH_LLAMA3_70B_ACCESS>
 python /opt/NeMo-Aligner/examples/nlp/gpt/serve_reward_model.py \
       rm_model_file=Llama3-70B-SteerLM-RM \
       trainer.num_nodes=1 \
@@ -125,23 +125,12 @@ E-Mail: [Zhilin Wang](mailto:[email protected])
 If you find this dataset useful, please cite the following works
 
 ```bibtex
-@misc{wang2023helpsteer,
-      title={HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM}, 
-      author={Zhilin Wang and Yi Dong and Jiaqi Zeng and Virginia Adams and Makesh Narsimhan Sreedhar and Daniel Egert and Olivier Delalleau and Jane Polak Scowcroft and Neel Kant and Aidan Swope and Oleksii Kuchaiev},
-      year={2023},
-      eprint={2311.09528},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL}
-}
-```
-
-```bibtex
-@misc{dong2023steerlm,
-      title={SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF}, 
-      author={Yi Dong and Zhilin Wang and Makesh Narsimhan Sreedhar and Xianchao Wu and Oleksii Kuchaiev},
-      year={2023},
-      eprint={2310.05344},
+@misc{wang2024helpsteer2,
+      title={HelpSteer2: Open-source dataset for training top-performing reward models}, 
+      author={Zhilin Wang and Yi Dong and Olivier Delalleau and Jiaqi Zeng and Gerald Shen and Daniel Egert and Jimmy J. Zhang and Makesh Narsimhan Sreedhar and Oleksii Kuchaiev},
+      year={2024},
+      eprint={2406.08673},
       archivePrefix={arXiv},
-      primaryClass={cs.CL}
+      primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
 }
 ```