Skip to main content
SpringerLink
Log in

The OpenELM Library: Leveraging Progress in Language Models for Novel Evolutionary Algorithms

  • Chapter
  • First Online:
Genetic Programming Theory and Practice XX

Part of the book series: Genetic and Evolutionary Computation ((GEVO))

  • 181 Accesses

Abstract

In recent years, Large Language Models (LLMs) have rapidly progressed in their capabilities in natural language processing (NLP) tasks, which have interestingly grown in scope to include generating computer programs. Indeed, recent studies have demonstrated how LLMs can enable highly proficient genetic programming (GP) algorithms and novel evolutionary algorithms more broadly. Motivated by these opportunities, this paper introduces OpenELM, an open-source Python library for designing evolutionary algorithms that leverage LLMs to intelligently generate variation, as well as to assess fitness and measures of diversity. The library includes implementations of several variation operators, and is designed to accommodate those with limited compute resources, by enabling fast inference, being runnable through hosted notebooks (such as Google Colab), and allowing for API-based LLMs to be used instead of local models run on GPUs. Additionally, OpenELM includes a variety of domain implementations for easy experimentation and adaptation, including several GP domains. The hope is to help researchers easily develop new approaches and applications within the nascent and largely unexplored paradigm of evolutionary algorithms that leverage LLMs.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 119.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 159.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    OpenELM is available at https://github.com/CarperAI/OpenELM.

  2. 2.

    Our diff models are released open-source alongside OpenELM, under an MIT license on the HuggingFace Hub repository.

    350M: https://huggingface.co/CarperAI/diff-codegen-350m-v2.

    2B: https://huggingface.co/CarperAI/diff-codegen-2b-v2.

    6B: https://huggingface.co/CarperAI/diff-codegen-6b-v2.

References

  1. OpenAI. Gpt-4 technical report (2023)

    Google Scholar 

  2. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Adv. Neural Inf. Process. Syst. 33, 1877 (2020)

    Google Scholar 

  3. Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H.W., Sutton, C., Gehrmann, S., et al.: arXiv:2204.02311 (2022)

  4. Askell, A., Bai, Y., Chen, A., Drain, D., Ganguli, D., Henighan, T., Jones, A., Joseph, N., Mann, B., DasSarma, N., et al.: arXiv:2112.00861 (2021)

  5. Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y.T., Li, Y., Lundberg, S., et al.: arXiv:2303.12712 (2023)

  6. Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H.P.D.O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al.: arXiv:2107.03374 (2021)

  7. Nijkamp, E., Pang, B., Hayashi, H., Tu, L., Wang, H., Zhou, Y., Savarese, S., Xiong, C.: arXiv preprint (2022)

    Google Scholar 

  8. Nijkamp, E., Hayashi, H., Xiong, C., Savarese, S., Zhou, Y.: arXiv:2305.02309 (2023)

  9. Jiang, N., Liu, K., Lutellier, T., Tan, L.: arXiv:2302.05020 (2023)

  10. Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N., Prabhumoye, S., Yang, Y., et al.: arXiv:2303.17651 (2023)

  11. Shinn, N., Labash, B., Gopinath, A.: arXiv:2303.11366 (2023)

  12. Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., McKinnon, C., et al.: arXiv:2212.08073 (2022)

  13. Sun, Z., Shen, Y., Zhou, Q., Zhang, H., Chen, Z., Cox, D., Yang, Y., Gan, C.: arXiv:2305.03047 (2023)

  14. Lehman, J., Gordon, J., Jain, S., Ndousse, K., Yeh, C., Stanley, K.O.: arXiv:2206.08896 (2022)

  15. Szerlip, P., Stanley, K.: In: ECAL 2013: The Twelfth European Conference on Artificial Life, pp. 218–225. MIT Press (2013)

    Google Scholar 

  16. Meyerson, E., Nelson, M.J., Bradley, H., Moradi, A., Hoover, A.K., Lehman, J.: arXiv:2302.12170 (2023)

  17. Chen, A., Dohan, D.M., So, D.R.: arXiv:2302.14838 (2023)

  18. Sudhakaran, S., González-Duque, M., Glanois, C., Freiberger, M., Najarro, E., Risi, S.: MarioGpt: Open-ended text2level generation through large language models (2023)

    Google Scholar 

  19. Xu, C., Sun, Q., Zheng, K., Geng, X., Zhao, P., Feng, J., Tao, C., Jiang, D.: arXiv:2304.12244 (2023)

  20. Gao, L., Biderman, S., Black, S., Golding, L., Hoppe, T., Foster, C., Phang, J., He, H., Thite, A., Nabeshima, N., et al.: arXiv:2101.00027 (2020)

  21. Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et al.: arXiv:2206.07682 (2022)

  22. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al.: Adv. Neural Inf. Process. Syst. 35, 27730 (2022)

    Google Scholar 

  23. Bradley, H., Dai, A., Zhang, J., Clune, J., Stanley, K., Lehman, J.: CarperAI Blog. https://carper.ai/quality-diversity-through-ai-feedback/ (2023)

  24. Lehman, J., Stanley, K.O.: In: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation, pp. 211–218 (2011)

    Google Scholar 

  25. Pugh, J.K., Soros, L.B., Stanley, K.O.: Frontiers in robotics and AI, p. 40 (2016)

    Google Scholar 

  26. Mouret, J.B., Clune, J.: arXiv:1504.04909 (2015)

  27. Flageat, M., Cully, A.: arXiv:2006.14253 (2020)

  28. Vassiliades, V., Chatzilygeroudis, K., Mouret, J.B.: IEEE Trans. Evol. Comput. 9 (2017). https://doi.org/10.1109/TEVC.2017.2735550. https://inria.hal.science/hal-01630627

  29. Ray, A., McCandlish, S.: Independent contribution (2020)

    Google Scholar 

  30. Bradley, H., Fan, H., Saini, H., Adithyan, R., Purohit, S., Lehman, J.: CarperAI Blog. https://carper.ai/diff-model/ (2023)

  31. Foundation, F.S.: Unified diff format. https://www.gnu.org/software/diffutils/manual/html_node/Unified-Format.html (2023). Accessed 02 Aug 2023

  32. Li, Z., Lu, S., Guo, D., Duan, N., Jannu, S., Jenks, G., Majumder, D., Green, J., Svyatkovskiy, A., Fu, S., et al.: arXiv:2203.09095 (2022)

  33. He, J., Beurer-Kellner, L., Vechev, M.: In: International Conference on Machine Learning (PMLR, 2022), pp. 8559–8580

    Google Scholar 

  34. Reimers, N., Gurevych, I.: In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3982–3992. Association for Computational Linguistics, Hong Kong, China (2019). https://doi.org/10.18653/v1/D19-1410. https://aclanthology.org/D19-1410

  35. Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., von Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Le Scao, T., Gugger, S., Drame, M., Lhoest, Q., Rush, A.: In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45. Association for Computational Linguistics, Online (2020). https://doi.org/10.18653/v1/2020.emnlp-demos.6. https://aclanthology.org/2020.emnlp-demos.6

  36. Chase, H.: Langchain. https://github.com/hwchase17/langchain (2023). Accessed 02 Aug 2023

  37. Corporation, N.: Triton Inference Server: an Optimized Cloud and Edge Inferencing Solution. https://github.com/triton-inference-server/server (2021). Accessed 02 Aug 2023

  38. Young, E.G., Zhu, P., Caraza-Harter, T., Arpaci-Dusseau, A.C., Arpaci-Dusseau, R.H.: In: Proceedings of the 11th USENIX Conference on Hot Topics in Cloud Computing, p. 16. USENIX Association, USA (2019). HotCloud’19

    Google Scholar 

  39. Schuster, T., Kalyan, A., Polozov, A., Kalai, A.T.: In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https://arxiv.org/abs/2106.05784 (2021)

  40. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)

    Google Scholar 

  41. Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al.: Adv. Neural Inf. Process. Syst. 35, 36479 (2022)

    Google Scholar 

  42. Harris, C.R., Millman, K.J., van der Walt, S.J., Gommers, R., Virtanen, P., Cournapeau, D., Wieser, E., Taylor, J., Berg, S., Smith, N.J., Kern, R., Picus, M., Hoyer, S., van Kerkwijk, M.H., Brett, M., Haldane, A., del Río, J.F., Wiebe, M., Peterson, P., Gérard-Marchant, P., Sheppard, K., Reddy, T., Weckesser, W., Abbasi, H., Gohlke, C., Oliphant, T.E.: Nat. 585(7825), 357 (2020). https://doi.org/10.1038/s41586-020-2649-2.

  43. Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.: In: International Conference on Machine Learning (PMLR, 2021), pp. 8748–8763

    Google Scholar 

  44. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Chi, E., Le, Q., Zhou, D.: arXiv:2201.11903 (2022)

  45. White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., Schmidt, D.C.: arXiv:2302.11382 (2023)

  46. Lester, B., Al-Rfou, R., Constant, N.: arXiv:2104.08691 (2021)

  47. Li, X.L., Liang, P.: arXiv:2101.00190 (2021)

  48. Zhou, Y., Muresanu, A.I., Han, Z., Paster, K., Pitis, S., Chan, H., Ba, J.: arXiv:2211.01910 (2022)

  49. Honovich, O., Shaham, U., Bowman, S.R., Levy, O.: arXiv:2205.10782 (2022)

  50. Biderman, S., Schoelkopf, H., Anthony, Q., Bradley, H., O’Brien, K., Hallahan, E., Khan, M.A., Purohit, S., Prashanth, U.S., Raff, E., et al.: arXiv:2304.01373 (2023)

  51. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al.: arXiv:2302.13971 (2023)

  52. Vassiliades, V., Chatzilygeroudis, K., Mouret, J.B.: IEEE Trans. Evol. Comput. 22, 623 (2016)

    Article  Google Scholar 

  53. Wang, R., Lehman, J., Rawal, A., Zhi, J., Li, Y., Clune, J., Stanley, K.: In: Proceedings of the 37th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol. 119, ed. by H.D. III, A. Singh (PMLR, 2020), Proceedings of Machine Learning Research, vol. 119, pp. 9940–9951. https://proceedings.mlr.press/v119/wang20l.html

  54. Haluptzok, P., Bowers, M., Kalai, A.T.: In: The Eleventh International Conference on Learning Representations. https://openreview.net/forum?id=SaRj2ka1XZ3 (2023)

  55. Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: arXiv:2106.09685 (2021)

  56. Li, R., Allal, L.B., Zi, Y., Muennighoff, N., Kocetkov, D., Mou, C., Marone, M., Akiki, C., Li, J., Chim, J., et al.: arXiv:2305.06161 (2023)

Download references

Author information

Authors and Affiliations

  1. CarperAI and EleutherAI and CAML Lab, University of Cambridge and Stability AI, Cambridge, UK

    Herbie Bradley

  2. EleutherAI and University of Geneva, Geneva, Switzerland

    Honglu Fan

  3. Aurecon Centre, Level 8, 850 Collins Street, 3008, Docklands, Melbourne VIC, Australia

    Theodoros Galanos

  4. EleutherAI and Queen’s University, Kingston, Canada

    Ryan Zhou

  5. EleutherAI and Georgia Institute of Technology, Atlanta, USA

    Daniel Scott

  6. CarperAI and StabilityAI, Newark, NJ, USA

    Joel Lehman

Authors
  1. Herbie Bradley
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Honglu Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Theodoros Galanos
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ryan Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Daniel Scott
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Joel Lehman
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Herbie Bradley .

Editor information

Editors and Affiliations

  1. School of Information, Communications and Media, University of Applied Sciences Upper Austria, Hagenberg, Austria

    Stephan Winkler

  2. Engineering Sciences Graduate Program, Tecnológico Nacional de México, IT de Tijuana, Tijuana, Baja California, Mexico

    Leonardo Trujillo

  3. Department of Computer Science and Engineering, Michigan State University, East Lansing, MI, USA

    Charles Ofria

  4. School of Computing, Queen's University, Kingston, ON, Canada

    Ting Hu

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Bradley, H., Fan, H., Galanos, T., Zhou, R., Scott, D., Lehman, J. (2024). The OpenELM Library: Leveraging Progress in Language Models for Novel Evolutionary Algorithms. In: Winkler, S., Trujillo, L., Ofria, C., Hu, T. (eds) Genetic Programming Theory and Practice XX. Genetic and Evolutionary Computation. Springer, Singapore. https://doi.org/10.1007/978-981-99-8413-8_10

Download citation

  • DOI: https://doi.org/10.1007/978-981-99-8413-8_10

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-99-8412-1

  • Online ISBN: 978-981-99-8413-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation