qwen2.5-3b-instruct-trl-sft-AlchObj

Model Card for qwen2.5-3b-instruct-trl-sft-AlchObj

This model is a fine-tuned version of Qwen/Qwen2.5-VL-3B-Instruct. It has been trained using TRL. It's trained to identify alchemic objects in historic book illustrations.

Quick start

from transformers import pipeline

question = """Which alchemic objects are in the image?
              Provide an answer in a well-structured JSON format with 12 classes (ampullae, animal, cucurbitae, cucurbitae-ambix,
              ollae, cucurbitae-retorte, cucurbitae-rosenhut, furnace, human, mineral-metal,
              other-equipment, plant) and the number of their occurences."""
generator = pipeline("text-generation", model="maychnix/qwen2.5-3b-instruct-trl-sft-AlchObj", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>

This model was trained with SFT.

Framework versions

• TRL: 0.16.0.dev0
• Transformers: 4.50.0.dev0
• Pytorch: 2.4.1+cu121
• Datasets: 3.3.2
• Tokenizers: 0.21.0

Citations

Cite TRL as:

@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}