metadata
base_model: Qwen/Qwen3-1.7B-Base
library_name: transformers
model_name: dracula-flow-base
tags:
- generated_from_trainer
- sft
- trl
licence: license
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}}
}