Model documentation & parameters

Language model: Type of language model to be used.

Text prompt: The text prompt to condition the model.

Maximal length: The maximal number of SMILES tokens in the generated molecule.

Decoding temperature: The temperature in the beam search decoding.

Prefix: A text prompt that will be passed to the mode before the prompt.

Top-k: Number of top-k probability tokens to keep.

Decoding-p: Only tokens with cumulative probabilities summing up to this value are kept.

Repetition penalty: Penalty for repeating tokens. Leave unchanged, but for CTRL model, use 1.2.

Model card -- HuggingFace

Model Details: Various Transformer-based language models.

Developers: HuggingFace developers

Distributors: HuggingFace developers' code integrated into GT4SD.

Model date: Varies between models.

Model type: Different types of transformers language models:

CTRL: CTRLLMHeadModel
GPT2: GPT2LMHeadModel
XLNet: XLNetLMHeadModel
OpenAIGPT: OpenAIGPTLMHeadModel
TransfoXL: TransfoXLLMHeadModel
XLM: XLMWithLMHeadModel

Information about training algorithms, parameters, fairness constraints or other applied approaches, and features: N.A.

Paper or other resource for more information: All documentation available from transformers documentation

License: MIT

Where to send questions or comments about the model: Open an issue on GT4SD repository.

Intended Use. Use cases that were envisioned during development: N.A.

Primary intended uses/users: N.A.

Out-of-scope use cases: Production-level inference, producing molecules with harmful properties.

Metrics: N.A.

Datasets: N.A.

Ethical Considerations: Unclear, please consult with original authors in case of questions.

Caveats and Recommendations: Unclear, please consult with original authors in case of questions.

Model card prototype inspired by Mitchell et al. (2019)

Citation

@article{manica2022gt4sd,
  title={GT4SD: Generative Toolkit for Scientific Discovery},
  author={Manica, Matteo and Cadow, Joris and Christofidellis, Dimitrios and Dave, Ashish and Born, Jannis and Clarke, Dean and Teukam, Yves Gaetan Nana and Hoffman, Samuel C and Buchan, Matthew and Chenthamarakshan, Vijil and others},
  journal={arXiv preprint arXiv:2207.03928},
  year={2022}
}