Remek

basal-omni-1.0-max

README

License: apache-2.0

Results

Served with the basal engine on one H100: basal-omni-1.0-max with --mode eager, bf16, one option order; basal-1.5-max as released (--mode fast, both option orders). Same items and the same clients for both.

Table with columns: benchmark, basal-omni-1.0-max (12B), basal-1.5-max (11B)
benchmark	basal-omni-1.0-max (12B)	basal-1.5-max (11B)
Werdykt v1, macro (hidden PL + EN, 10 categories × 2 languages)	0.823	0.773
PL decisions (held-out test of basal-1.0, 7,081 items)	0.954	0.940
PL general (knowledge, exams, reading; 3,079 items)	0.810	0.797
PL-Real (300 real Polish documents)	0.980	0.970
EN external panel (10 public English decision tasks, 3,842 items)	0.789	0.737
Coverage at 1% error (share decided automatically with the shipped threshold)	47.4%¹	62.2%

Werdykt v1: 0.823 (95% interval 0.813–0.832; Polish 0.824, English 0.821), 5.0 points above basal-1.5-max, served with --deterministic (one request per forward; at most 0.1 point from the default mode on our tests). Weakest categories: rules (0.418; compute exact thresholds and dates in code), long documents (0.742) and contracts (0.762).
English: it is ahead on the English external panel (+5.2 points; BIG-Bench Hard 0.809 vs 0.644, TabFact 0.873 vs 0.750; behind on ContractNLI, 0.720 vs 0.740), and on the English corpus test of 1,479 items (0.724 vs 0.659).
Polish: it is ahead on the PL decisions test (+1.4 points, 95% interval +0.8 to +2.0), and level on Polish general knowledge (+1.3) and PL-Real (+1.0), whose intervals include zero.
¹ Coverage: per question type, at 0.47% observed error. A type without a certified threshold is deferred: at the 1% target, score questions go to a person. basal-1.5-max's 62.2% used one threshold pooled over all types; under that rule this model reaches 65.1% at 1.02% error.

Quick start

1. Install into a fresh uv environment:

bash

uv venv --python 3.12 --allow-existing ~/basal-env && source ~/basal-env/bin/activateuv pip install torch==2.11.0 torchvision==0.26.0 --index-url https://download.pytorch.org/whl/cu128uv pip install "basal[media] @ https://github.com/rkinas/basal/archive/refs/tags/v2.0.0.tar.gz"

2. Start the server. It prints basal: model ... ready:

bash

basal-serve --model Remek/basal-omni-1.0-max --mode eager --media on --port 8000

This release runs in the engine's eager mode only (PyTorch, bf16, about 24 GB of GPU memory). The fast mode (shared prefix, CUDA graphs), the FP8 checkpoints and the MLX / GGUF ports of basal-1.5 come with a later release of this line.

3. Ask questions, exactly as with basal-1.5:

bash

curl -s localhost:8000/v1/systemone -H 'content-type: application/json' -d '{  "state": "Klient: od wczoraj nie mogę zalogować się do bankowości internetowej, system pokazuje błąd hasła.",  "questions": {    "dept":   {"type": "choice", "instructions": "Do którego działu skierować zgłoszenie?",               "criteria": {"cards": "Reklamacje kart", "online": "Wsparcie bankowości elektronicznej", "loans": "Kredyty"}},    "urgent": {"type": "noul", "instructions": "Czy klient nie może korzystać z usługi?"}}}'

Full API (multi, act, option keys, max_error): API.

Images and audio

With --media on, a request may carry images and audio with its state. They are placed where the state text goes, before it, in the order given; the state text may be empty.

bash

IMG=$(base64 < paragon.jpg | tr -d '\n')curl -s localhost:8000/v1/systemone -H 'content-type: application/json' -d '{  "state": "", "lang": "pl",  "media": [{"type": "image", "data": "'"$IMG"'"}],  "questions": {    "card": {"type": "noul", "instructions": "Czy zapłacono kartą?"},    "vat":  {"type": "choice", "instructions": "Jaka jest najwyższa stawka VAT na paragonie?",             "criteria": {"23": "23%", "8": "8%", "5": "5%", "0": "0% lub zwolniony"}}}}'

"media": a list of {"type": "image" | "audio", "data": "<base64>"} (a data: URL works too). Images: any format Pillow reads. Audio: WAV, FLAC, OGG or MP3, any sample rate (mixed to mono, resampled to 16 kHz), at most 30 s a clip.
"detail": "default" (280 image tokens) or "high" (1,120; small print, slower).
"lang": "pl" or "en", the prompt language when the state text does not show it (a state that is only media).
Limits: 8 items and 20 MB each per request, 50 MP per image.
Mixed media: one request may mix images and audio, and every question sees all of them. In our test (20 pairs of a document image and a spoken request), adding the other medium changed 10–25% of the answers. For the steadiest answers, send each question with only the media it is about.
Answers carry : the temperatures and the certified thresholds were fitted on text; validate the thresholds on your own media before automating with them.

On omni-probe-pl, our small Polish probe (each item asked from the media and from its text):

Table with columns: probe, items, from the media, from the text, untrained Gemma 4 12B, from the media
probe	items	from the media	from the text	untrained Gemma 4 12B, from the media
decision from an image of a rendered document	160	0.838	0.900 (the document's text)	0.675
decision about a real photo	150	0.660	0.527 (the question alone)	0.680
intent of a spoken request (MINDS-14)	140	0.714	0.929 (transcript)

Rendered documents are read almost as well as their text (6 points behind), and photos add 13 points over the question alone.
Speech scores 22–42 points below its transcript and stays at the untrained base's level: send a transcript when you have one.

Speed

One question per request, one option order, on one H100 (--mode eager, bf16, --media on):

Table with columns: measurement, result
measurement	result
sequential, 200 requests	66 ms p50 / 95 ms p95 per question
32 concurrent clients, 1,000 requests	19.0 decisions/s

basal-1.5-max in its fast engine: 27.3 ms p50 and 33.4 decisions/s on the same test.
On Werdykt's 5,000 items (longer states, 16 concurrent clients): 4.2 decisions/s, 76 ms p50 / 1.36 s p95 (basal-1.5-max in its fast engine: 4.6 decisions/s).
--orders 2 costs about twice as much per question.
Long states (up to ~30k tokens measured) are prefilled in 2,048-token chunks.

Files

model-*.safetensors, tokenizer, chat_template.jinja, processor_config.json: the model.
- Gemma 4 architecture, 12B, 262k vocabulary.
- Gemma's image and audio encoders are included and unchanged (this release is trained on text); the engine reads media through them with --media on (processor_config.json).
CALIBRATION.json: per-type temperatures and certified confidence thresholds for 1% / 5% error, fitted on the served engine (--mode eager, bf16, one option order).
CALIBRATION.o2.json: the same for --orders 2 (both option orders averaged).
basal.json: prompt format 2 and the readout protocol.

How it works

The model receives a fixed chat prompt with the state, the question and coded options (A–Z, then two-character codes, up to 255). The assistant turn is prefilled with {"answer": ", and the decision is the softmax over the next-token logits of the option codes only: one forward pass, no text generation. The server applies the calibrated temperature of the question type from CALIBRATION.json.

Use the confidence. CALIBRATION.json stores thresholds for a target error of 1% or 5% among accepted decisions. They were chosen on calibration data before testing; on the test data they accept 47.4% / 82.9% of decisions at 0.47% / 3.9% observed error (at the 1% target score questions have no certified threshold and are deferred). Accept decisions above the threshold automatically and route the rest to a person.

Training

Base and method: fine-tuned from google/gemma-4-12B-it with LoRA (rank 32) on the language-model layers. The vision and audio parts were not trained.
Data: about 815,000 typed decisions in Polish and English: rules and deadlines, real documents, long documents, retrieval decisions, contracts, routing, ordinal scores, judging answers, agent and tool decisions, and "cannot be determined" answers.
Distillation: basal-1.5 provides soft targets on the decisions it answers correctly.
Schedule: one epoch of 815,386 decisions (12,741 steps of 64; the basal-1.7 mix without its 1,931 items longer than 6,144 tokens) at learning rate 3e-5.

Limitations

Experimental. It is the first model of a new base; validate it on your own documents before relying on it.
Images and audio are zero-shot. Gemma 4's encoders read them, but this model was trained on text decisions only; media answers are weaker than text where the media itself is hard (phone photos, speech), see "Images and audio". Their calibration is the text calibration.
Speed: the eager engine only; it is slower than basal-1.5-max in the fast mode.
Exact arithmetic and thresholds are a weak spot of one-pass decisions: compute them in code.
Option order: one order is asked by default; --orders 2 reduces sensitivity to option order at twice the cost.
Review: decisions with serious consequences for people should be reviewed by a person.

Citation

bibtex

@software{kinas2026basal20,  title   = {basal-2.0: typed-decision models and inference engine for Polish and English},  author  = {Kinas, Remigiusz},  year    = {2026},  version = {2.0.0},  url     = {https://github.com/rkinas/basal}} @techreport{kinas2026basal,  title       = {basal-1.0: Reliable, Highly Optimized Typed Decisions for Polish},  author      = {Kinas, Remigiusz},  institution = {ai5},  year        = {2026},  type        = {Technical report},  doi         = {10.5281/zenodo.23022986},  url         = {https://doi.org/10.5281/zenodo.23022986}}

License and attribution

Apache-2.0. Fine-tuned from google/gemma-4-12B-it (Apache-2.0).

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

Remek

Model Tree

Base

google/gemma-4-12B-it

Fine-tuned

this model

Input Modalities

TextAudioImageVideo

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Results

Table with columns: benchmark, basal-omni-1.0-max (12B), basal-1.5-max (11B)
benchmark	basal-omni-1.0-max (12B)	basal-1.5-max (11B)
Werdykt v1, macro (hidden PL + EN, 10 categories × 2 languages)	0.823	0.773
PL decisions (held-out test of basal-1.0, 7,081 items)	0.954	0.940
PL general (knowledge, exams, reading; 3,079 items)	0.810	0.797
PL-Real (300 real Polish documents)	0.980	0.970
EN external panel (10 public English decision tasks, 3,842 items)	0.789	0.737
Coverage at 1% error (share decided automatically with the shipped threshold)	47.4%¹	62.2%

Werdykt v1: 0.823 (95% interval 0.813–0.832; Polish 0.824, English 0.821), 5.0 points above basal-1.5-max, served with --deterministic (one request per forward; at most 0.1 point from the default mode on our tests). Weakest categories: rules (0.418; compute exact thresholds and dates in code), long documents (0.742) and contracts (0.762).
English: it is ahead on the English external panel (+5.2 points; BIG-Bench Hard 0.809 vs 0.644, TabFact 0.873 vs 0.750; behind on ContractNLI, 0.720 vs 0.740), and on the English corpus test of 1,479 items (0.724 vs 0.659).
Polish: it is ahead on the PL decisions test (+1.4 points, 95% interval +0.8 to +2.0), and level on Polish general knowledge (+1.3) and PL-Real (+1.0), whose intervals include zero.
¹ Coverage: per question type, at 0.47% observed error. A type without a certified threshold is deferred: at the 1% target, score questions go to a person. basal-1.5-max's 62.2% used one threshold pooled over all types; under that rule this model reaches 65.1% at 1.02% error.

Quick start

1. Install into a fresh uv environment:

bash

uv venv --python 3.12 --allow-existing ~/basal-env && source ~/basal-env/bin/activateuv pip install torch==2.11.0 torchvision==0.26.0 --index-url https://download.pytorch.org/whl/cu128uv pip install "basal[media] @ https://github.com/rkinas/basal/archive/refs/tags/v2.0.0.tar.gz"

2. Start the server. It prints basal: model ... ready:

bash

basal-serve --model Remek/basal-omni-1.0-max --mode eager --media on --port 8000

3. Ask questions, exactly as with basal-1.5:

bash

curl -s localhost:8000/v1/systemone -H 'content-type: application/json' -d '{  "state": "Klient: od wczoraj nie mogę zalogować się do bankowości internetowej, system pokazuje błąd hasła.",  "questions": {    "dept":   {"type": "choice", "instructions": "Do którego działu skierować zgłoszenie?",               "criteria": {"cards": "Reklamacje kart", "online": "Wsparcie bankowości elektronicznej", "loans": "Kredyty"}},    "urgent": {"type": "noul", "instructions": "Czy klient nie może korzystać z usługi?"}}}'

Full API (multi, act, option keys, max_error): API.

Images and audio

With --media on, a request may carry images and audio with its state. They are placed where the state text goes, before it, in the order given; the state text may be empty.

bash

IMG=$(base64 < paragon.jpg | tr -d '\n')curl -s localhost:8000/v1/systemone -H 'content-type: application/json' -d '{  "state": "", "lang": "pl",  "media": [{"type": "image", "data": "'"$IMG"'"}],  "questions": {    "card": {"type": "noul", "instructions": "Czy zapłacono kartą?"},    "vat":  {"type": "choice", "instructions": "Jaka jest najwyższa stawka VAT na paragonie?",             "criteria": {"23": "23%", "8": "8%", "5": "5%", "0": "0% lub zwolniony"}}}}'

"media": a list of {"type": "image" | "audio", "data": "<base64>"} (a data: URL works too). Images: any format Pillow reads. Audio: WAV, FLAC, OGG or MP3, any sample rate (mixed to mono, resampled to 16 kHz), at most 30 s a clip.
"detail": "default" (280 image tokens) or "high" (1,120; small print, slower).
"lang": "pl" or "en", the prompt language when the state text does not show it (a state that is only media).
Limits: 8 items and 20 MB each per request, 50 MP per image.
Mixed media: one request may mix images and audio, and every question sees all of them. In our test (20 pairs of a document image and a spoken request), adding the other medium changed 10–25% of the answers. For the steadiest answers, send each question with only the media it is about.
Answers carry : the temperatures and the certified thresholds were fitted on text; validate the thresholds on your own media before automating with them.

On omni-probe-pl, our small Polish probe (each item asked from the media and from its text):

Table with columns: probe, items, from the media, from the text, untrained Gemma 4 12B, from the media
probe	items	from the media	from the text	untrained Gemma 4 12B, from the media
decision from an image of a rendered document	160	0.838	0.900 (the document's text)	0.675
decision about a real photo	150	0.660	0.527 (the question alone)	0.680
intent of a spoken request (MINDS-14)	140	0.714	0.929 (transcript)

Rendered documents are read almost as well as their text (6 points behind), and photos add 13 points over the question alone.
Speech scores 22–42 points below its transcript and stays at the untrained base's level: send a transcript when you have one.

Speed

One question per request, one option order, on one H100 (--mode eager, bf16, --media on):

Table with columns: measurement, result
measurement	result
sequential, 200 requests	66 ms p50 / 95 ms p95 per question
32 concurrent clients, 1,000 requests	19.0 decisions/s

basal-1.5-max in its fast engine: 27.3 ms p50 and 33.4 decisions/s on the same test.
On Werdykt's 5,000 items (longer states, 16 concurrent clients): 4.2 decisions/s, 76 ms p50 / 1.36 s p95 (basal-1.5-max in its fast engine: 4.6 decisions/s).
--orders 2 costs about twice as much per question.
Long states (up to ~30k tokens measured) are prefilled in 2,048-token chunks.

Files

model-*.safetensors, tokenizer, chat_template.jinja, processor_config.json: the model.
- Gemma 4 architecture, 12B, 262k vocabulary.
- Gemma's image and audio encoders are included and unchanged (this release is trained on text); the engine reads media through them with --media on (processor_config.json).
CALIBRATION.json: per-type temperatures and certified confidence thresholds for 1% / 5% error, fitted on the served engine (--mode eager, bf16, one option order).
CALIBRATION.o2.json: the same for --orders 2 (both option orders averaged).
basal.json: prompt format 2 and the readout protocol.

How it works

Training

Base and method: fine-tuned from google/gemma-4-12B-it with LoRA (rank 32) on the language-model layers. The vision and audio parts were not trained.
Data: about 815,000 typed decisions in Polish and English: rules and deadlines, real documents, long documents, retrieval decisions, contracts, routing, ordinal scores, judging answers, agent and tool decisions, and "cannot be determined" answers.
Distillation: basal-1.5 provides soft targets on the decisions it answers correctly.
Schedule: one epoch of 815,386 decisions (12,741 steps of 64; the basal-1.7 mix without its 1,931 items longer than 6,144 tokens) at learning rate 3e-5.

Limitations

Experimental. It is the first model of a new base; validate it on your own documents before relying on it.
Images and audio are zero-shot. Gemma 4's encoders read them, but this model was trained on text decisions only; media answers are weaker than text where the media itself is hard (phone photos, speech), see "Images and audio". Their calibration is the text calibration.
Speed: the eager engine only; it is slower than basal-1.5-max in the fast mode.
Exact arithmetic and thresholds are a weak spot of one-pass decisions: compute them in code.
Option order: one order is asked by default; --orders 2 reduces sensitivity to option order at twice the cost.
Review: decisions with serious consequences for people should be reviewed by a person.

Citation

bibtex

@software{kinas2026basal20,  title   = {basal-2.0: typed-decision models and inference engine for Polish and English},  author  = {Kinas, Remigiusz},  year    = {2026},  version = {2.0.0},  url     = {https://github.com/rkinas/basal}} @techreport{kinas2026basal,  title       = {basal-1.0: Reliable, Highly Optimized Typed Decisions for Polish},  author      = {Kinas, Remigiusz},  institution = {ai5},  year        = {2026},  type        = {Technical report},  doi         = {10.5281/zenodo.23022986},  url         = {https://doi.org/10.5281/zenodo.23022986}}

License and attribution

Apache-2.0. Fine-tuned from google/gemma-4-12B-it (Apache-2.0).