textrm1.5-25M-bizmail
A 25.95M parameter Transformer-based model that generates surprisingly coherent business-style emails.
Github: https://github.com/kamisori-daijin/textrm
Overview
This project explores how far a small (~25M parameter) model can go in generating structured business email text.
The model is not fully instruction-following and may produce inconsistent or mixed outputs, but it can often generate realistic email-like text.
Features
- Small size (~25M parameters)
- Generates business-style email text
- Works best with simple prompts
- Occasionally produces surprisingly coherent outputs
Limitations
- Weak instruction following
- May mix multiple prompts or contexts
- Inconsistent tone and intent
- Not suitable for production use
Example
Prompt: Write a professional business email
Output: Dear [Competitor Name], Thank you for reaching out and suggesting the [Feature Name] feature. We appreciate you bringing this to our attention. However, due to the current industry situation and a partial system outage at [Company Name], we are unable to proceed at this time. We would be happy to revisit this discussion in the future. Please let us know your availability for a brief call next week. Sincerely, [Name] Security Researcher
Training
Architecture: TRM (custom Transformer variant)
Parameters: 25.95M
Dataset: Synthetic business email dataset (generated using Gemma3-4B) Link: https://huggingface.co/datasets/Kamisori-daijin/email-datasets-20k
Training epochs: 18
Usage
- Clone this repository
- Install dependencies:
pip install torch transformers tqdm - Run inference: python inference.py
Notes
This model is intended for research and experimentation purposes only.
License
Apache2
Disclaimer
This model was trained on synthetic data generated using Gemma3-4B (Google). This project is independent and does not replicate or fine-tune Gemma3-4B.