---
license: apache-2.0
tags:
- pytorch
- gpt2
- molecule-compound
pipeline_tag: text-generation
---

# molcrawl-compounds-guacamol-gpt2-small

## Model Description

GPT-2 small (124M parameters) fine-tuned on [GuacaMol](https://github.com/BenevolentAI/guacamol) SMILES data, starting from the `molcrawl-compounds-gpt2-small` pre-trained model.

The tokenizer is a character-level BPE tokenizer (vocab_size=612). Input SMILES strings should be passed **without** spaces. The `[SEP]` token (id=13) is used as the end-of-sequence marker.

## Datasets

- **GuacaMol**: [https://github.com/BenevolentAI/guacamol](https://github.com/BenevolentAI/guacamol) (Fine-tuning dataset)

- **Model Type**: gpt2
- **Data Type**: Molecule/Compound
- **Training Date**: 2026-04-24

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained("kojima-lab/molcrawl-compounds-guacamol-gpt2-small")
tokenizer = AutoTokenizer.from_pretrained("kojima-lab/molcrawl-compounds-guacamol-gpt2-small")

# Generate SMILES string
prompt = "CC(=O)O"
input_ids = tokenizer.encode(prompt, return_tensors="pt")
with torch.no_grad():
    output_ids = model.generate(
        input_ids,
        max_new_tokens=50,
        do_sample=True,
        temperature=0.8,
        eos_token_id=tokenizer.convert_tokens_to_ids("[SEP]"),  # [SEP] is EOS for compounds
        pad_token_id=0,
    )
print(tokenizer.decode(output_ids[0], skip_special_tokens=True))

```

## Source Code

Training pipeline, configuration files, and data preparation scripts are
available in the MolCrawl GitHub repository:
[https://github.com/mmai-framework-lab/MolCrawl](https://github.com/mmai-framework-lab/MolCrawl)

## License

This model is released under the APACHE-2.0 license.

## Citation

If you use this model, please cite:

```bibtex
@misc{molcrawl_compounds_guacamol_gpt2_small,
  title={molcrawl-compounds-guacamol-gpt2-small},
  author={{RIKEN}},
  year={2026},
  publisher={{Hugging Face}},
  url={{https://huggingface.co/kojima-lab/molcrawl-compounds-guacamol-gpt2-small}}
}
```