gupta-tanish

llama-7b-dpo-baseline

gupta-tanish/llama-7b-dpo-baseline

llama-7b-dpo-baseline is a text generation model from gupta-tanish. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.

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