Tag

#TRL

2 articles

Auditing Preference Biases and Fine-Tuning Language Models with Direct Preference Optimization on Anthropic HH-RLHF Using TRL and LoRA

This article explains Direct Preference Optimization (DPO), a method for fine-tuning language models using preference data, and how it can be implemented using TRL and LoRA tools. It also discusses the importance of auditing preference data for biases.

Aug 1934

A Coding Guide on LLM Post Training with TRL from Supervised Fine Tuning to DPO and GRPO Reasoning

Learn how to improve large language models using post-training techniques like Supervised Fine-Tuning, Reward Modeling, DPO, and GRPO with the TRL library.

May 194