dracula-flow-base

Model Card for dracula-flow-base

This model is a fine-tuned version of Qwen/Qwen3-1.7B-Base. It has been trained using TRL.

This has been specifically trained on Dracula flow 1-5 for 6 epochs to get it to be semi decent enough at writing dracula flow bars. It is not advised to use it as an actual dracula flow generator but rather as a generator for synthetic data to then train the real dracula flow model.

Quick start

from transformers import pipeline

prompt = "[dracula flow]: "
generator = pipeline("text-generation", model="None", device="cuda")
output = generator(prompt, max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.26.2
• Transformers: 4.57.3
• Pytorch: 2.7.0
• Datasets: 4.4.2
• Tokenizers: 0.22.2

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 Gallou{\'e}dec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}