learn.ifs.name

Tülu 3: Pushing Frontiers in Open Language Model Post-Training

Lambert et al., 2024, Tülu 3 (arXiv preprint arXiv:2411.15124)

Subscriber deck — free during early access

1 cards in “2.3 Tülu 3 Recipe” · whole deck

2.3 Tülu 3 Recipe

  1. What are the four stages of the Tülu 3 recipe?
    (1) Curating prompts aimed at core skills (knowledge, reasoning, math, coding, instruction following, chat, safety); (2) supervised fine-tuning; (3) preference tuning with DPO on partly on-policy data; (4) reinforcement learning with verifiable rewards (RLVR). All stages are guided by one evaluation suite.
    • Lambert et al., 2024, Tülu 3 (arXiv preprint arXiv:2411.15124), §2.3

Source

  • Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Xinxi Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, Noah A. Smith, Yizhong Wang, Pradeep Dasigi and Hannaneh Hajishirzi. 2024. Tülu 3: Pushing Frontiers in Open Language Model Post-Training. In arXiv preprint arXiv:2411.15124. https://arxiv.org/abs/2411.15124