Model Card for gemma-text-to-bill

This model is a fine-tuned version of google/gemma-3-1b-it. 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="peanutpan/gemma-text-to-bill", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Example

Question:

<bos><start_of_turn>user
给定交易文本 <USER_QUERY> 当前时间是2025年4月25日， 从中识别出：1. 金额（数值型），2. 商户全称（最长的名称），3. 交易时间（格式：yyyy-MM-dd）。返回JSON格式：{ "amount": double, "company": str, "time": str }
<USER_QUERY>
PY市场-虚拟物品购买
文化休闲
今天10:06
-5.00
</USER_QUERY><end_of_turn>

Answer:

{"amount":-5.0,"company":"PY市场","time":"2025/04/25"}

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.15.2
• Transformers: 4.51.3
• Pytorch: 2.6.0+cu124
• Datasets: 3.3.2
• Tokenizers: 0.21.1

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}}
}