Fully open
Weights, code and training data all published: OLMo, Pythia, BLOOM. 19 models on EveryLLM so far.
Fully open models publish everything needed to study or rebuild them: the weights, the training data or a precise recipe for it, the training and evaluation code, and often intermediate checkpoints saved during training. They are rarer than open-weights releases because gathering lawful data and documenting it takes work. EleutherAI's Pythia, BigScience's BLOOM, Ai2's OLMo and Switzerland's Apertus are the reference points.
Why release the data
Without the data, outsiders cannot check what a model learned from, test whether benchmark questions leaked into its training, or study how abilities emerge. EleutherAI's Pythia suite (April 2023) released 16 models from 70 million to 12 billion parameters trained on the same public data in the same order, with 154 checkpoints each. Ai2's OLMo (February 2024) released its Dolma dataset, code, logs and checkpoints alongside the weights.
Definitions
The Open Source Initiative published version 1.0 of its Open Source AI Definition on 28 October 2024. It asks for the weights and code under open terms, and for enough detail about the data that a skilled person could build a substantially equivalent system, without always requiring the raw data itself. Apertus, released on 2 September 2025 by EPFL, ETH Zurich and the Swiss National Supercomputing Centre, published its data recipes and code.
Famous fully open models
Still to be written: OLMo (language model).