---
license: apache-2.0
datasets:
- HuggingFaceH4/ultrafeedback_binarized
language:
- en
- fr
base_model:
- NousResearch/Nous-Hermes-llama-2-7b
- meta-llama/Llama-2-7b
pipeline_tag: text-generation
metrics:
- accuracy
- bertscore
- bleurt
- brier_score
tags:
- biology
- chemistry
---

Trained NousResearch/Nous-Hermes-llama-2-7b on UltraFeedback for Direct Preference Optimization on the preference data created on Ultrafeedback having difference b/w chosen score and rejected score>=5