OLMo: Accelerating the Science of Language Models
Groeneveld et al., 2024, OLMo (Proceedings of the 62nd Annual Meeting of ACL (Volume 1: Long Papers))
Subscriber deck — free during early access
1 cards in “4.3 Adaptation Evaluation” · whole deck
4.3 Adaptation Evaluation
- How much did adaptation help OLMo-7B?Instruction tuning on the Tülu mix and then DPO greatly improved chat and safety scores (e.g. ToxiGen, TruthfulQA), with OLMo beating most other chat variants, though still behind Tülu 2 built on Llama 2, for which that data mix was designed.
- Groeneveld et al., 2024, OLMo (Proceedings of the 62nd Annual Meeting of ACL (Volume 1: Long Papers)), §4.3, p. 15796
Source
- Dirk Groeneveld, Iz Beltagy, Evan Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew Peters, Valentina Pyatkin, Abhilasha Ravichander, Dustin Schwenk, Saurabh Shah, William Smith, Emma Strubell, Nishant Subramani, Mitchell Wortsman, Pradeep Dasigi, Nathan Lambert, Kyle Richardson, Luke Zettlemoyer, Jesse Dodge, Kyle Lo, Luca Soldaini, Noah Smith and Hannaneh Hajishirzi. 2024. OLMo: Accelerating the Science of Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15789–15809. License: CC BY 4.0. Flashcards adapted from this work. doi:10.18653/v1/2024.acl-long.841 https://aclanthology.org/2024.acl-long.841/