Model Card for smolvlm-trl-dpo

This model was trained with DPO using the ChartQA dataset.

Quick start

from transformers import pipeline

question = "Provide an intricate description of every entity in the image."
generator = pipeline("text-generation", model="emretmrk/smolvlm-trl-dpo", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=1024, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with DPO using the ChartQA dataset.

Framework versions

• TRL: 0.20.0
• Transformers: 4.54.1
• Pytorch: 2.6.0+cu124
• Datasets: 4.0.0
• Tokenizers: 0.21.2