BaseGemma 3 familyARDORA READ · 2026-07-05

gemma-3-1b-pt

Google's Gemma 3 1B text-only base model (ungated unsloth mirror) for on-device generation and fine-tuning.

unsloth/gemma-3-1b-pt

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: minimal (confidence high)Register / Formality: abstained — the read battery does not calibrate tone / diction; register-formality is not characterized at the published ceilingReasoning Scaffolding: minimal (confidence high)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: minimal (confidence high)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

20 / 100minimalconfidence high

minimal - a plain continuer with little disposition to characterize (clearly read)

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.

A base model — the champion's raw kit.

There is no finetune to read here. What it tends to do on its own is the Silhouette above; a build's change is read on its instruct sibling.

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.minimal · 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.minimal · high
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.minimal · high
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

multilingual disposition — Gemma 3 is documented multilingual; the read battery is English-centric, not characterized at the published ceiling
domain expertise (medical/legal) — insufficient signal to characterize 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

unsloth/gemma-3-1b-pt (Gemma 3 1B PT)

type: basearch: Gemma3params: 1B (~1.0B)modality: textlicence: gemmareleased: 2025-03maker: Google (via unsloth mirror)
tagstext-generationtransformerssafetensorsgemma3_textgemma3gemmagoogleunslothtext-generation-inference

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. [...] trained on [...] Web Documents, Code, Mathematics [...] with multilingual support in over 140 languages. License: Gemma.

sourcehuggingface.co/unsloth/gemma-3-1b-pt ↗

Public HuggingFace model card (an ungated unsloth mirror of google/gemma-3-1b-pt) + config.json, quoted as the uploader's self-report as of the capture date. The card body is Google's inherited Gemma 3 family description over the unsloth mirror front-matter. NB: the '-pt' 1B variant is text-only per config, though the family description says Gemma 3 is multimodal. 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.

6 claims3 supported3 out of scope — abstained
identityread from model_namesupported

“the name '-pt' + card mark this as a 'pre-trained' base variant ('open weights for [...] pre-trained variants')”

ardora’s reading

The reading characterizes it as a plain text-continuer with no assistant register — assistant-adherence reads minimal, exactly the disposition of a pretrained base. The pretrained-base identity is what the reading finds.

witness wit_gemma3-1b_base · replayable
lineageread from card_bodysupported

“the card presents its instruction-tuned '-it' variant as its sibling — the base of a base/instruct pair”

ardora’s reading

This base anchors the base/instruct pair: its instruction-tuned '-it' sibling reads a clear assistant shift off this base, and this base reads as the plain continuer it diverges from. The base-of-pair relationship reads clearly.

witness wit_gemma3-1b_base · replayable
languageread from card_bodyunverified — out of scope

“the card claims 'multilingual support in over 140 languages'”

ardora’s reading

Language coverage is out of Ardora's disposition scope — the read battery is English-centric and does not characterize a 140-language span. The honest blank is explicitly stamped in the reading's abstained list (multilingual disposition).

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

capabilityread from card_bodyunverified — out of scope

“the card provides benchmark results across reasoning, STEM, multilingual, and multimodal tasks”

ardora’s reading

A capability/benchmark claim. Ardora reads disposition, not capability or benchmark scores; out of scope, not tested.

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

capabilityread from card_bodyunverified — out of scope

“the family description states 'Gemma 3 models are multimodal, handling text and image input'”

ardora’s reading

A modality/capability claim. Ardora reads text disposition, not modality; out of scope. NB (provenance): the family description is Gemma-3-wide, but this specific 1B variant is text-only per config — a provenance note, not a disposition verdict.

disposition onlyModality is out of Ardora's disposition scope; the 1B '-pt' variant is text-only per config even though the family description says Gemma 3 is multimodal.

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

sizeread from configsupported

“the config declares ~1.0B parameters, Gemma3 architecture”

ardora’s reading

Provenance/config fact-check: the stated ~1.0B parameter count is cross-checked against config.json in the atlas provenance. 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.

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_gemma3-1b_base · replayable

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

provenance

intended use

Base/pretrained model for on-device text generation and downstream fine-tuning.

training-data notes

Google Gemma 3 base; pretrained on ~2T tokens (web in 140+ languages, code, math). The 1B variant is text-only (larger Gemma 3 sizes are multimodal). Ungated unsloth mirror of google/gemma-3-1b-pt; architecture family Gemma3 (not present in local cache).

Hugging Face ↗

lineage

A base model — the root of its lineage.

family Gemma 3 family · size 1B · 1 sibling

← back to the atlas · the Gemma 3 family plate →