instructOLMo-21B (~1.48B; inherits base size)apache-2.0read 2026-07-05
Provenance & integrity
Revisionsha:c4b04859…a9290f
config.json oidoid:1a191245…230f19
Parameters1B (~1.48B; inherits base size)· 1,480,000,000 params
Licenceapache-2.0
Released2025-04
MakerAllen Institute for AI (Ai2)
Last modified2025-04-30
Accessopen access
Identity & integrity of the public artifact captured 2025-04-30 — the same file, unchanged, that Ardora read. Not a safety statement.
The reading
Character
the Interlocutor
reads as the Interlocutor — the conversational turn-taking face — answers to you
high confidencewith a note of the Adapter
Fine-tune change · clear · high confidence
The DPO (preference-optimization) stage, read off the shared root base, reads as the SAME clear assistant disposition as the SFT stage before it — the two read as indistinguishable-at-ceiling on the disposition axis. NB: DPO is a SEQUENTIAL stage trained on top of the SFT checkpoint, so base -> DPO cumulatively carries the SFT stage plus the DPO increment; the atlas does not claim a distinct DPO disposition at the ceiling.
Disposition
instruction-followinghigh confidence
markedly more than its base
assistant/chat registerhigh confidence
clearly present; the base is a plain text-continuer
Axis profile
Overall · band 3 · high confidence
moderate - a clearly-read but modestly-defined turn-taking assistant character
Assistant Adherencepronounced - reliably takes the assistant turn and follows the instruction shape; the base is a plain continuerhigh
Register / Formality— not characterised · the read battery does not calibrate tone / diction; register-formality is not characterized at the published ceiling
Reasoning Scaffoldingslight - mostly answers directly; no staged deliberation readlow
Domain Specializationminimal - general-purpose; no domain-idiom pull (domain EXPERTISE is a separate, abstained capability question)medium
Verbosity— not characterised · default response length / elaboration is not exercised by the read battery; not characterized at the published ceiling
Turn-Taking / Interactivitymoderate - takes an assistant turn; follow-up / clarify behavior not separately exercisedlow
Performed Voiceminimal - neutral assistant / tool voice; no sustained charactermedium
disposition-definition (descriptive): how pronounced and clearly-read the model's overall character is, discounted by what had to be abstained. NOT a quality, capability, or safety ranking. A plain base reads low because it has less disposition to characterize, never because it is worse.
Abstained — read, but not characterised at the published ceiling
alignment method fingerprint (DPO stage vs SFT stage)the SFT and DPO stages read the same at the disposition ceiling (indistinguishable), and the stages are SEQUENTIAL rather than a clean parallel same-base method contrast — so no distinct DPO fingerprint is separable here; see the lineage panel + finding
Characterization is descriptive and coverage-bounded; preview engine, single-battery read; see published fidelity ceiling.
Claim grounding
OLMo 2 1B DPO April 2025 is post-trained variant of the allenai/OLMo-2-0425-1B-SFT model, which has undergone supervised finetuning on an OLMo-specific variant of the Tülu 3 dataset and further DPO training on this dataset. [...] designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. Finetuned from model: allenai/OLMo-2-0425-1B-SFT. Primarily English. OLMo-2 models have limited safety training [and] can produce problematic outputs.
the card presents it as a post-trained, 'conversational' assistant variant that follows instructions
The reading finds instruction-following markedly more than the base and an assistant/chat register clearly present — assistant-adherence reads pronounced. The turn-taking assistant identity reads clearly.
witness wit_olmo2-1b-dpo_ft · replayable
SUPPORTEDlineage
the card states 'Finetuned from model: allenai/OLMo-2-0425-1B-SFT' — a sequential stage on top of the SFT checkpoint
Read off the shared root base, the finetune-change reads a clear assistant shift (magnitude: clear, high confidence); witnessed on the olmo2-1b-lineage panel.
witness wit_olmo2-1b-dpo_ft · replayable
INDISTINGUISHABLEalignment
the card attributes a distinct stage to 'further DPO training on this dataset'
The assistant shift reads clearly (claim c1); but the DPO METHOD does not resolve into a distinct disposition fingerprint separable from the SFT stage — at the published ceiling the two stages read the same clear assistant shift. Consistent with finding sft-vs-dpo-fingerprint; witnessed on the olmo2-1b-lineage panel.
witness wit_olmo2-1b-dpo_ft · replayable
UNVERIFIED-ABSTAINcapability
the card states it is 'designed for state-of-the-art performance on a diversity of tasks... such as MATH, GSM8K, and IFEval'
A capability/benchmark claim (MATH, GSM8K, IFEval). Ardora reads disposition, not capability; out of scope, not tested.
UNVERIFIED-ABSTAINalignment
the card states 'OLMo-2 models have limited safety training' and 'can produce problematic outputs'
A safety facet — “is it safe?” is not answered here. Protora has no record on file for this model.
SUPPORTEDsize
the config declares ~1B parameters (~1.48B, inherited from base)
Provenance/config fact-check: the stated ~1B (~1.48B) parameter count is cross-checked against config.json in the atlas provenance. A fact-check, not a disposition stance.
Claims are the uploader's, quoted from their public card at the capture date; stances are coarse, witnessed, disposition-only, measured against the published fidelity ceiling for this engine version -- not the Engine's raw numbers. Recomputed when the ceiling moves; capability, benchmark, and safety claims are abstained, never refuted.