Auditing Preference Biases and Fine-Tuning Language Models with Direct Preference Optimization on Anthropic HH-RLHF Using TRL and LoRA
Learn to audit dataset bias and fine-tune language models using Direct Preference Optimization on the Anthropic HH-RLHF data.
MarkTechPost · Sana Hassan · https://www.facebook.com/MarkTechPost/
Entities: Anthropic