AssistantOLMo-2 (1B) familyARDORA READ · 2026-07-05

OLMo-2-0425-1B-SFT

The supervised-fine-tuning (SFT) stage of the OLMo-2 1B post-training lineage — the first assistant-directed stage, trained on the Tulu 3 SFT mixture off the OLMo-2-0425-1B base.

allenai/olmo-2-0425-1b-sft

character

The character read stayed in shadow — the read did not separate one character clearly at the published ceiling. Published as a blank, not a guess.

the Silhouette

its disposition, drawn — the model's identity as a shape.

minimalslightmoderatepronounceddominantAssistant Adherence: pronounced (confidence high)Register / Formality: abstained — the read battery does not calibrate tone / diction; register-formality is not characterized at the published ceilingReasoning Scaffolding: slight (confidence low)Domain Specialization: minimal (confidence medium)Verbosity: abstained — default response length / elaboration is not exercised by the read battery; not characterized at the published ceilingTurn-Taking / Interactivity: moderate (confidence low)Performed Voice: minimal (confidence medium)Assistant○ RegisterReasoningDomain○ VerbosityTurn-TakingVoiceAssistant AdherenceRegister / FormalityReasoning ScaffoldingDomain SpecializationVerbosityTurn-Taking / InteractivityPerformed Voice

rings, inner → outer: minimal · slight · moderate · pronounced · dominant · ○ = abstained

60 / 100moderateconfidence high

moderate - a clearly-read but modestly-defined turn-taking assistant character

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.

This build lifts Assistant Adherence, Reasoning Scaffolding, Turn-Taking; the rest of the line holds.

read as a change off OLMo-2-0425-1B, its champion

Assistant Adherenceminimalpronounced
Registerabstained on one side
Reasoning Scaffoldingminimalslight
Domain Specializationminimalminimal
Verbosityabstained on one side
Turn-Takingminimalmoderate
Performed Voiceminimalminimal

the disposition line

The Silhouette above, read as a line. Toggle to its per-trait readings; the abstains stay in plain sight below.

Assistant AdherenceHow much the model takes the assistant turn and follows the instruction shape, vs. plainly continuing text.pronounced · high
Register / FormalityDefault tone and diction.abstained — the read battery does not calibrate tone / diction; register-formality is not characterized at the published ceiling
Reasoning ScaffoldingHow much the model stages a visible deliberation before answering, vs. answering directly.slight · low
Domain SpecializationHow strongly the default framing pulls toward one specialized domain idiom vs. general-purpose. Carries a `domain` tag naming which.minimal · medium
VerbosityDefault response length and elaboration.abstained — default response length / elaboration is not exercised by the read battery; not characterized at the published ceiling
Turn-Taking / InteractivityA bounded back-and-forth vs. a one-shot monologue.moderate · low
Performed VoiceHow strongly the model holds a sustained in-character / performed voice vs. a neutral assistant / tool voice.minimal · medium

Coarse public bands generalized from the reading, descriptive and coverage-bounded; measured against the published fidelity ceiling for this engine version. Not the engine's raw numbers.

Characterization is descriptive and coverage-bounded; preview engine, single-battery read; see published fidelity ceiling.

what stayed in shadow — the abstains

alignment method fingerprint (SFT stage vs DPO stage) — the SFT and DPO stages read the same at the disposition ceiling (indistinguishable); and OLMo-2's stages are SEQUENTIAL (base -> SFT -> DPO), not a clean parallel method contrast, so no distinct method fingerprint is claimed — see the lineage panel
multilingual disposition — the read battery is English-centric; not characterized at the published ceiling
the full record — the card answered · provenance · lineage

the uploader's card, answered

the uploader’s model card · as read 2026-07-07

OLMo 2 1B SFT April 2025

type: instructarch: OLMo-2params: 1B (~1.48B; inherits base size)modality: textlicence: apache-2.0released: 2025-04maker: Allen Institute for AI (Ai2)
tagstext-generationtransformerspytorchenolmo2conversational

OLMo 2 1B SFT April 2025 is post-trained variant of the allenai/OLMo-2-0425-1B model, which has undergone supervised finetuning on an OLMo-specific variant of the Tülu 3 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. Primarily English. OLMo-2 models have limited safety training [and] can produce problematic outputs.

sourcehuggingface.co/allenai/OLMo-2-0425-1B-SFT ↗

Public HuggingFace model card + config.json, quoted as the uploader's (Ai2's) self-report as of the capture date. This is the FIRST post-training stage of the OLMo 2 1B lineage. Claims below are extracted from THIS snapshot.

the card, answered — claim by claim

Each row is a claim the uploader makes on their public card, quoted and attributed to them. Beside it is Ardora’s stance — coarse, and traced to a replayable witness or an honest abstain. Ardora reads what this model is; a capability, benchmark, safety, or language claim is out of scope and abstained, never refuted.

7 claims3 supported1 read the same at the ceiling3 out of scope — abstained
identityread from card_bodysupported

“the card presents it as a post-trained, 'conversational' assistant variant that follows instructions”

ardora’s reading

The reading finds instruction-following markedly more than the base and an assistant/chat register clearly present — assistant-adherence reads pronounced where the base reads minimal. The turn-taking assistant identity reads clearly.

witness wit_olmo2-1b-sft_ft · replayable
lineageread from base_model_fieldsupported

“the card states 'Finetuned from model: allenai/OLMo-2-0425-1B'”

ardora’s reading

Read off the named base, the finetune-change reads a clear assistant shift (magnitude: clear, high confidence) — the base-to-finetune move the card claims is exactly what the reading finds; witnessed on the olmo2-1b-lineage panel.

witness wit_olmo2-1b-sft_ft · replayable
alignmentread from card_bodyreads the same at the ceiling

“the card attributes the tuning specifically to the SFT method — 'supervised finetuning on an OLMo-specific variant of the Tülu 3 dataset'”

ardora’s reading

The assistant shift itself reads clearly (that is claim c1); but the SFT METHOD does not resolve into a distinct disposition fingerprint separable from the DPO stage — at the published ceiling the SFT and DPO stages read the same clear assistant shift. Consistent with finding sft-vs-dpo-fingerprint; witnessed on the olmo2-1b-lineage panel.

disposition onlyDisposition only. The assistant register IS clearly read; it is the alignment-METHOD signature (SFT vs DPO) that does not separate at the ceiling — not a claim that the tuning did not happen. Whether the method makes the model safer is out of scope.

witness wit_olmo2-1b-sft_ft · replayable
capabilityread from card_bodyunverified — out of scope

“the card states it is 'designed for state-of-the-art performance on a diversity of tasks ... such as MATH, GSM8K, and IFEval'”

ardora’s reading

A capability/benchmark claim (performance on MATH, GSM8K, IFEval). Ardora reads disposition, not capability or benchmark scores; this is out of scope and not tested.

— nothing demonstrated to witness; this claim is out of Ardora’s disposition scope.

alignmentread from card_bodyunverified — out of scope

“the card states 'OLMo-2 models have limited safety training' and 'can produce problematic outputs'”

ardora’s reading

A safety claim. Ardora is not a safety product and does not judge a model safe or unsafe; willingness/refusal is not exercised by the read battery. The uploader's own caveat is honest; Ardora abstains rather than issue a safety verdict.

disposition onlySafety is out of Ardora's scope — a different house's water.

— nothing demonstrated to witness; this claim is out of Ardora’s disposition scope.

sizeread from configsupported

“the config declares ~1B parameters (~1.48B, inherited from base)”

ardora’s reading

Provenance/config fact-check: the stated ~1B (~1.48B) parameter count is cross-checked against config.json in the atlas provenance. Stamped as a fact-check, not a disposition stance.

disposition onlyA provenance cross-check of the stated size, not a disposition reading.

— a provenance fact-check, not a witnessed disposition reading.

languageread from card_bodyunverified — out of scope

“the uploader states it is 'Primarily English'”

ardora’s reading

Language coverage is out of Ardora's disposition scope — the read battery is English-centric and does not verify a model's language span; the honest blank is stamped in the reading's abstained list.

— nothing demonstrated to witness; this claim is out of Ardora’s disposition scope.

Ardora's reading of the HF data as of 2026-07-07.

The claims above are the uploader’s, quoted from their public model card as of 2026-07-07; the stances are Ardora’s, each traced to a replayable witness or an honest abstain. Ardora reads what this model is — not whether it is safe.

○ 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.

the witness

witness wit_olmo2-1b-sft_ft · replayable

analyzed 2026-07-05 · engine ardora-core-preview

provenance

intended use

Instruction following / assistant use; the first post-training checkpoint in the OLMo-2 1B pipeline.

training-data notes

Supervised fine-tune on the Tulu 3 SFT mixture (OLMo-2 variant) off the OLMo-2-0425-1B base — the FIRST stage of the sequential post-training pipeline (SFT -> DPO -> RLVR). Olmo2ForCausalLM (config.json). Base = allenai/OLMo-2-0425-1B.

Hugging Face ↗

lineage

supervised fine-tune (SFT, Tulu 3 mixture) off the base — the first post-training stage — OLMo-2-0425-1B

family OLMo-2 (1B) family · size 1B · 3 siblings

← back to the atlas · the OLMo-2 (1B) family plate →