notesum.ai
Published at November 22TÜLU 3: Pushing Frontiers in Open Language Model Post-Training
cs.CL
Released Date: November 22, 2024
Authors: Nathan Lambert1, Jacob Morrison1, Valentina Pyatkin1, Shengyi Huang1, Hamish Ivison1, Faeze Brahman1, Lester James V. Miranda1, Alisa Liu1, Nouha Dziri1, Shane Lyu, Yuling Gu1, Saumya Malik1, Victoria Graf1, Jena D. Hwang1, Jiangjiang Yang1, Ronan Le Bras1, Oyvind Tafjord1, Chris Wilhelm1, Luca Soldaini1, Noah A. Smith1, Yizhong Wang1, Pradeep Dasigi1, Hannaneh Hajishirzi1
Aff.: 1Allen Institute for AI
![[Uncaptioned image]](https://arxiv.org/html/2411.15124v1/x1.png)
| Model Checkpoints | ||
| Stage | Llama 3.1 8B | Llama 3.1 70B |
| Base Model | meta-llama/Llama-3.1-8B | meta-llama/Llama-3.1-70B |
| SFT | allenai/Llama-3.1-Tulu-3-8B-SFT | allenai/Llama-3.1-Tulu-3-70B-SFT |
| DPO | allenai/Llama-3.1-Tulu-3-8B-DPO | allenai/Llama-3.1-Tulu-3-70B-DPO |
| Final Models | ||
| (RLVR) | allenai/Llama-3.1-Tulu-3-8B | |
| RM: allenai/Llama-3.1-Tulu-3-8B-RM | allenai/Llama-3.1-Tulu-3-70B | |