---
license: mit
library_name: transformers
pipeline_tag: text-generation
tags:
- biology
- plasmid
- dna
- synthetic-biology
- gpt2
---

# PlasmidGPT

A HuggingFace-compatible repackaging of [PlasmidGPT](https://github.com/lingxusb/PlasmidGPT) (Shao, 2024) — a GPT-2-style decoder pretrained on 153k engineered plasmid sequences from Addgene. Loadable with standard `AutoModelForCausalLM` and `AutoTokenizer`. Used as the base for [PlasmidGPT-SFT](https://huggingface.co/UCL-CSSB/PlasmidGPT-SFT) and [PlasmidGPT-GRPO](https://huggingface.co/UCL-CSSB/PlasmidGPT-GRPO).

## Quick start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("UCL-CSSB/PlasmidGPT")
tokenizer = AutoTokenizer.from_pretrained("UCL-CSSB/PlasmidGPT")

input_ids = tokenizer("ATG", return_tensors="pt").input_ids
outputs = model.generate(input_ids, max_new_tokens=512, do_sample=True, temperature=1.0)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Citation

```bibtex
@article{shao2024plasmidgpt,
  title   = {{PlasmidGPT}: a generative framework for plasmid design and annotation},
  author  = {Shao, Bin},
  journal = {bioRxiv},
  year    = {2024},
  doi     = {10.1101/2024.09.30.615762}
}
```