Update README.md

README.md

@@ -92,8 +92,6 @@ OpenBioLLM-8B is an advanced open source language model designed specifically fo
 <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png">
 </div>
 
-
-- **Reward Model**: [Nexusflow/Starling-RM-34B](https://huggingface.co/Nexusflow/Starling-RM-34B)
 - **Policy Optimization**: [Fine-Tuning Language Models from Human Preferences (PPO)](https://arxiv.org/abs/1909.08593)
 - **Ranking Dataset**: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar)
 - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)
@@ -107,7 +105,7 @@ This combination of cutting-edge techniques enables OpenBioLLM-8B to align with
 - **Language(s) (NLP):** en
 - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs 
 - **License:** Meta-Llama License 
-- **Fine-tuned from models:** [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) & [Starling-RM-34B](https://huggingface.co/Nexusflow/Starling-RM-34B)
+- **Fine-tuned from models:** [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B)
 - **Resources for more information:**
     - Paper: Coming soon