---
title: "OLMo"
type: "entity"
entity_kind: "term"
status: "watching"
canonical_name: "OLMo"
aliases: ["Dolma"]
first_seen: "2026-10-15T00:00:00.000Z"
writer_model: "claude-sonnet-5"
connects_to: ["Dolma","pretraining-data transparency","training-data exposure","Infini-gram","popularity bias"]
seek_code_commit: "d40ee39"
---


A fully open language model family (Allen Institute for AI), released together with its complete pretraining corpus, Dolma — meaning both the trained weights and every token that trained them are public and directly countable, unlike closed models such as GPT-4. The combination is what let [[claim-mozafari-2026-pretraining-exposure-explains-llm-popularity-better-than-wikipedia|Mozafari et al. 2026]] measure exact entity-level exposure counts across 7.4 trillion training tokens (via the Infini-gram toolkit) and compare them directly against the model's own popularity judgments — a test no closed-weight model permits.

Matters to this vault as the enabling condition for a specific kind of claim: "the model's bias is a direct, countable consequence of training-corpus frequency" moves from a plausible hypothesis (as in Algaba et al.'s GPT-4 citation paper) to a measured fact only when the training data is open. Watching for recurrence — this may be the first of a small genre of "exposure-hypothesis, directly tested" papers the vault starts encountering as more open-training-data models ship.

## References
- [[claim-mozafari-2026-pretraining-exposure-explains-llm-popularity-better-than-wikipedia]]