Model Card for online-dpo-qwen2-4

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on the trl-lib/ultrafeedback-prompt dataset. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="qgallouedec/online-dpo-qwen2-4", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=500)[0]
print(output["generated_text"][1]["content"])

Training procedure

This model was trained with Online DPO, a method introduced in Direct Language Model Alignment from Online AI Feedback.

Framework versions

• TRL: 0.12.0.dev0
• Transformers: 4.45.0.dev0
• Pytorch: 2.4.1
• Datasets: 3.0.0
• Tokenizers: 0.19.1