Model X-Ray evidence correction — 6 September 2026. Any structural-location, knowledge-separation, portrait-visualization, lesion-response, legacy simulated-quantization, robustness or prior X-Ray endorsement previously linked from this card has been withdrawn. It is not current evidence. No replacement result is published while validation remains pending. Correction record.
Tetracta VAN-1B
Why this model exists: VAN-1B is the deliberately-vanilla transformer control we train
alongside our own architecture, on the same data, so that comparisons mean something.
Its counterpart — Z-Next 1B, no attention and no KV cache, with a session state that does
not grow with context — is documented here, with a live demo you can talk to:
· Z-Next 1B results & benchmarks
· Full results page
· Live demo →
A 0.94B-parameter decoder-only transformer trained from scratch on 10.32B tokens — one epoch, no data repetition — then instruction-tuned on 11,419 examples.
This model is a data-efficiency demonstration and a measurement instrument, not a production assistant.
Its value is that we kept the raw pre-trained state, the SFT data, and every intermediate checkpoint — which let
us measure what instruction tuning actually does to a model. Those measurements are in the paper below.
🌐 tetracta.ai — Tetracta, independent AI research lab
📄 Paper:"What does SFT do? Measuring a 0.94B model from the inside and the outside" → tetracta.ai
That split is the paper's thesis: behaviour alignment can be taught with very little data; knowledge and
reasoning cannot — those need scale. We won exactly the lanes SFT teaches, and lost exactly the lanes
pre-training scale gives.
Model details
Architecture
Decoder-only transformer — deliberately vanilla, nothing proprietary here
Measured: 4/6 correct tool calls. The mechanism works — but read limitation 3 before relying on it.
Limitations — measured, not guessed
Reasoning and arithmetic are not reliable. Multi-step problems collapse.
Factual accuracy is weak. It fabricates on rare or detailed facts.
It corrupts digits when copying a tool result into its answer (tool returns 2726784 → model writes
2762784; it sometimes leaks raw JSON into the sentence). Render tool results programmatically instead of
trusting the model to repeat them.
Without the tool runtime attached it may invent live data ("the weather in Paris is…").
It is inconsistent about its own abilities — it sometimes claims internet access.
For calibration: Qwen2.5-1.5B-Instruct made the same error in our panel, answering "Yes, I can browse the
internet." 1,750× more training data did not fix self-knowledge.
English only. There is no Turkish in the pre-training corpus.
Long-form writing is clearly behind (writing lane 0-8 — not one judge picked us).
Our judges are models, not humans.
What SFT cost, measured
Instruction tuning moved only 0.68 % of the weights — and overwhelmingly in the embedding layer (5.35 %),
leaving normalisation layers essentially untouched (0.04 %). What it actually did was collapse output entropy
from 5.951 to 1.795 (peak probability 0.279 → 0.730). The price: held-out plain-text loss rose 11.5 %
(bpc 4.340 → 4.839). Almost the entire tax was paid in the first SFT round; a second, targeted round added
only ~1 % more while fixing safety, identity and pronoun resolution.
Method and full numbers in the paper.
Intended use
Reasonable: research on data efficiency and instruction tuning · a clean, fully documented base for your own
SFT experiments · tool routing and intent classification inside a program that validates the output ·
teaching, since every artifact is published.
Not reasonable: anything where a wrong fact or a wrong number matters. Do not run it unsupervised.
Citation
bibtex
1@misc{tetracta_van1b_2026,
2 title = {Tetracta VAN-1B: What does SFT do? Measuring a 0.94B model from the inside and the outside},
3 author = {Tetracta},
4 year = {2026},
5 url = {https://tetracta.ai}
6}
Training data provenance
Fully documented, and deliberately boring — we chose reproducible public corpora so the comparison would be
checkable, and excluded synthetic data on purpose (it can carry hallucinations of its own, which would have
contaminated exactly what we set out to measure).
~12.5B raw tokens → filtering and MinHash dedup → 10.32B trained tokens, one epoch. Attribution to both
sources is required by their licenses and gladly given.
Instruction-tuning data is not published with this model.
License
Apache-2.0 for the weights, code and model card in this repository.
Chosen deliberately: this model exists to be examined and built on, not to be gated. Apache-2.0 also carries an
explicit "AS IS", no-warranty and limitation-of-liability clause — which matters for a model whose measured
failure modes (unreliable arithmetic, digit corruption when copying tool results, weak factual recall) are listed
above in full. Use it accordingly.
If you build on it, a link back to tetracta.ai is appreciated but not required.
