[KongchangAI]
ModelOLMo系列

OLMo

A series of open-source large language models released by the Allen Institute for AI. The project fully discloses model weights, the training dataset (Dolma), data processing pipelines, training code, and checkpoints from all training stages, and is widely recognized in academia as the closest implementation to a truly open-source large language model.

Timeline (last 90 days)

Sep 7

OLMo (Open Language Model) is a fully open-source large language model series led by the Allen Institute for AI (AI2); OLMo-3 is its third-generation version, with training data, code, and weights all fully open-sourced.

Unverified50%

All Facts (1)

Unverified

OLMo (Open Language Model) is a fully open-source large language model series led by the Allen Institute for AI (AI2); OLMo-3 is its third-generation version, with training data, code, and weights all fully open-sourced.

50%

Source Articles

Ai2 Olmo-core 3: The Secret Behind 2.7x MoE Training ThroughputOct 14SGUID: Distilling a Lean Skill Library for Co-Evolution of LLM Skills and ModelsOct 13Ai2's Byte-Level Language Model Published in Nature: A New Path Beyond TokenizersOct 12The Truth Behind LLM 'Personalities': The Gap Between Self-Image and Actual Behavior in 22 Large Language ModelsSep 16The Truth About Open-Source AI: You Got the Cake, Not the RecipeSep 15