# OnePass: caliber-flex-1b

> Caliber Flex 1B by OnePass. Decision-only model, exactly 1,000,000,000 parameters.

- Page: https://systemonemodels.ai/onepass-st/caliber-flex-1b
- API: https://api.systemonemodels.ai/v1/models/onepass-st/caliber-flex-1b
- Download: `pip install systemonemodels && systemone pull onepass-st/caliber-flex-1b`

## Facts

| | |
|---|---|
| Maker | OnePass (https://systemonemodels.ai/onepass-st) |
| Decides | choice, noul, score |
| Architecture | llm |
| Base model | qwen/qwen3.5-0.8b-base |
| Licence | caliber-flex-non-commercial-1.0 |
| Availability | Open weights |
| Latest version | 0.1.0 |

## Model card

# Caliber Flex 1B by OnePass

Decision-only model: no chat, no completions. You send a text plus
questions, it returns picks with calibrated probabilities.

Exactly **1,000,000,000 parameters**: Qwen3.5-0.8B-Base (Apache-2.0)
depth-upscaled with 7 grafted top layers, trained LoRA r17, two-layer
decision head (183→4392) with fitted temperature T=1.548. Counted, not
rounded. Forecast reading taught by a TimesFM 3.0 teacher
(non-commercial). English + Russian.

## Files

| File | What |
|---|---|
| `caliber-flex-1b-Q8_0.gguf` | Backbone + LoRA, Q8_0 quant. Generative/embedding use (chat, RAG). |
| `hybrid_adapter.pt` | Decision head + LoRA + temperature. Needed for decisions. |
| `merged/` | Full bf16 transformers model (backbone + LoRA merged). |
| `infer.py` | Standalone decisions, works offline. |
| `Modelfile` | Ollama import for the GGUF. |

The GGUF alone does not answer decisions — the scoring head lives in
`hybrid_adapter.pt` and runs through `infer.py` (transformers).
The GGUF is the same backbone for open use: chat, embeddings, evals.

## Decisions (transformers)

```bash
pip install torch transformers peft
python infer.py --state "Ticket #4411: two charges, refund one." \
  --type choice --options billing shipping access
python infer.py --state "Тикет #1234: дважды списали деньги." \
  --type choice --options billing shipping access
```

```json
{
  "model": "caliber-flex-1b",
  "choice": "billing",
  "probabilities": {"billing": 0.91, "shipping": 0.04, "access": 0.05},
  "confidence": 0.87,
  "route_to_human": false
}
```

Three question types: `choice` (one of N), `noul` (yes/no probability),
`score` (ordered levels, answered with the mean). No evidence in the
state → flat probabilities and `"route_to_human": true`.

| Metric | Value |
|---|---|
| Held-out accuracy | 0.800 |
| Brier | 0.074 |
| ECE | 0.037 |
| Temperature | 1.548 |

## GGUF (Ollama / llama.cpp)

```bash
ollama create caliber-flex-1b -f Modelfile
ollama run caliber-flex-1b
```

Ask it who it is and it answers itself — the identity is in the weights,
no system prompt involved.

## Notes

8k context inherited from training, not re-validated past it. Calibrated
on the sets above (acc 0.80, Brier 0.074, ECE 0.037) — re-check thresholds
on your own labels before automating anything. Commercial use is out:
the TimesFM teacher permits research and personal use only, and this
license carries that forward. The served `model` field stays
`caliber-flex-1b by OnePass`; don't strip it.

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models