Tulu

Creator

Creator

Created

Created

2023 Jul 9 18:54

Editor

Editor

Edited

Edited

2025 Feb 1 14:32

Refs

Refs

Tulu 2

allenai/tulu-2-dpo-70b · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

allenai/tulu-2-dpo-70b · Hugging Face

https://huggingface.co/allenai/tulu-2-dpo-70b

allenai/tulu-2-dpo-70b · Hugging Face

allenai/tulu-65b · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

allenai/tulu-65b · Hugging Face

https://huggingface.co/allenai/tulu-65b

allenai/tulu-65b · Hugging Face

OLMo 2 (LLM) Tulu3 (Training Framework)

Tülu 3 opens language model post-training up to more tasks and more people | Ai2

Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes designed to serve as a comprehensive guide for modern post-training techniques.

Tülu 3 opens language model post-training up to more tasks and more people | Ai2

https://allenai.org/blog/tulu-3

Tülu 3 opens language model post-training up to more tasks and more people | Ai2

2 OLMo 2 Furious

We present OLMo 2, the next generation of our fully open language models. OLMo 2 includes dense autoregressive models with improved architecture and training recipe, pretraining data mixtures, and...

2 OLMo 2 Furious

https://arxiv.org/abs/2501.00656

2 OLMo 2 Furious

Tulu 3

Scaling the Tülu 3 post-training recipes to surpass the performance of DeepSeek V3 | Ai2

Introducing Tülu 3 405B, the first application of fully open post-training recipes to the largest open-weight models.

Scaling the Tülu 3 post-training recipes to surpass the performance of DeepSeek V3 | Ai2

https://allenai.org/blog/tulu-3-405B

Scaling the Tülu 3 post-training recipes to surpass the performance of DeepSeek V3 | Ai2

Recommendations

////////