---
title: decision-4b-v1.2
canonical_url: "https://www.modelscope.cn/models/flymy-ai/decision-4b-v1.2"
md_url: "https://www.modelscope.cn/models/flymy-ai/decision-4b-v1.2.md"
repository: flymy-ai/decision-4b-v1.2
last_updated: 2026-09-25
license: apache-2.0
base_model:
  - Qwen/Qwen3.5-4B
base_model_relation: adapter
library_name:
  - lora
  - peft
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 49
stars: 0
tags:
  - lora
  - peft
  - typed-decisions
  - calibration
  - jevbench
  - qwen3.5
---

# decision-4b-v1.2

> decision-4b-v1.2 - flymy-ai 在 ModelScope 开源的模型。Decision 4B v1.2 (FlyMyJev-4B, preview)

flymy-ai/decision-4b-v1.2 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可，基于 Qwen/Qwen3.5-4B 构建。

- **Repository**: flymy-ai/decision-4b-v1.2
- **License**: apache-2.0
- **Base model**: Qwen/Qwen3.5-4B
- **Tags**: lora, peft, typed-decisions, calibration, jevbench, qwen3.5
- **Downloads**: 49
- **Stars**: 0
- **Last updated**: 2026-09-25

Source: https://www.modelscope.cn/models/flymy-ai/decision-4b-v1.2

---

# Decision 4B v1.2 (FlyMyJev-4B, preview)

An open model for **typed decisions**: give it a state (a ticket, a policy and a case, a log, an answer to judge) and a
question with a closed set of answers (`noul` yes/no, `choice`, `score`), and it returns a probability for every
declared option in **one forward pass**. Nothing is generated. Independent project: not a release of TypeSafe, not
affiliated with it, not a reconstruction of Jev's closed implementation.

Run `qwen35_4b_letter_h10_v64b`. Every number below is our own measurement; we make no claim about a JevBench rank.

## What it is

| | |
|---|---|
| Base | `Qwen/Qwen3.5-4B` at revision `851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a` (Apache-2.0), downloaded separately |
| Adapter | LoRA rank 16, alpha 32, dropout 0.05 on the attention projections of both layer kinds (q_proj, k_proj, v_proj, o_proj, in_proj_qkv, in_proj_z, in_proj_a, in_proj_b, out_proj); 14.4M trainable parameters |
| Prompt | the chat template with thinking disabled; one JSON user message `{evidence, criterion, options[{letter, description}]}`, descriptions `"<key>: <text>"`, yes/no options `true` then `false` (SemIf's format, MIT) |
| Readout | the option letters' logits at the last prompt token (fp32 projection of its hidden state), softmax at the temperature in `model.json` (1.45, fitted on our own data only) |
| Output | a distribution over exactly the declared options: a label outside that set cannot come out |
| Serving | the LoRA is folded into the base at load; one CUDA graph per padded input length; p50 19.3 ms / p95 22.7 ms per short decision on one RTX 4090 (eager 59 ms); the same answer as the eager path on 120/120 checked items |
| Inputs | up to 16,384 tokens |

## Use

```python
import model                       # this repository's model.py
m = model.load()                   # verifies every file against manifest.json, downloads the pinned base on first use
m.decide("Refunds need a receipt and a purchase within 30 days. The customer bought 12 days ago and has no receipt.",
         {"type": "noul", "instructions": "Is a refund permitted under the policy?"})
# {'probabilities': {'true': ..., 'false': ...}, 'input_tokens': ..., 'seconds': ...}
```

JevBench: `server.py` serves TypeSafe's `/v1/systemone` wire format for the `typesafe` adapter; `jevbench_adapter.py`
is an in-process adapter; `run_jevbench.py` runs the official runner without editing its registry. Set
`FLYMYJEV_DEVICE=cpu` to run on CPU (slow, no CUDA graphs).

## Results (our measurements)

The frozen base and this adapter were measured on the same GPU in the same session with the same prompt; changes are
paired (fixed / broken items). JevBench's judge tier and sealed set are not public and are not included.

| set | frozen Qwen3.5-4B | this model | fixed / broken | reference |
|---|---:|---:|---:|---|
| JevBench public, hard (111) | 61.3 | **78.4** | 24 / 5 | Jev 1.13: 74.1 on the full hard tier (220 items, 109 held out) |
| JevBench public, standard (72) | 97.2 | **95.8** | 2 / 3 |  |
| JevBench public, easy (48) | 97.9 | **100.0** | 1 / 0 |  |
| JevBench public, all 231 | 80.1 | **88.3** | 27 / 8 | Jev 1.13: 86.6 |
| our hard dev set (160, 8 families) | 42.5 | **66.9** | 51 / 12 | Jev 1.13: 57.5 |
| our real-case sets v1-v3 (407) | 88.9 | **90.9** | 24 / 16 | Jev 1.13: 94.6 / 97.8 / 98.9 on v1 / v2 / v3 |

- Hard dev set by family (frozen -> this model): multi-hop lookups 30 -> 70, date and number decisions 10 -> 45, trade-offs 25 -> 60, adversarial traps 50 -> 85, abstention 60 -> 90, paraphrase robustness 55 -> 85, long policies 55 -> 55, answer judging 55 -> 45 (20 items per family).
- Calibration on the public hard tier at the served temperature: ECE 0.070, fidelity to exact gold
  distributions 87.3 (1 - mean total variation distance).
- Real-case set v3 puts the gold at option A in 46 % of its choice items; the frozen base's first-option habit scores
  there, and training removes it. Read v3 with that in mind.

## Package check (25 Sep 2026)

This package, as published, was run on one RTX 4090 against the JevBench v1.4.2 harness on the 231 public items: the official runner with `jevbench_adapter.py` and `server.py` with the harness's `typesafe` adapter both read 203/231 (easy 48/48, standard 69/72, hard 86/111). Details: `package_check.json`.

## Training

One run from the base, no merging of runs and no ensembles: 2 epochs, 862 steps of at
most 12,288 padded tokens (9.5M tokens), lr 3e-05 with warm-up and cosine decay,
cross-entropy on the option-letter logits (the exact distribution where an item declares one), choice options shuffled
on every pass, seed 99. The recipe shape follows JevK5 v0.2 (allebee/jevk5, Apache-2.0).

Data: our own decision data and licence-reviewed public datasets. No JevBench item and no output of Jev was used for
training, tuning or model selection.

## Benchmark hygiene

- The temperature was fitted on our own calibration split and hard dev set, never on benchmark items.
- The gates that made this run a release candidate were declared before the run.
- The JevBench public items were used to measure, and once to diagnose: comparing our frozen outcomes with SemIf's
  published per-item outcomes showed that our first yes/no rendering lost about 5 points on yes/no items; we adopted
  SemIf's rendering everywhere. No training data was chosen or built from public items.

## Limitations

- One pass of a 4B model: no step-by-step reasoning. Chained arithmetic and long multi-hop documents stay weak.
- Messages where two options are both true under a one-answer schema are untested.
- English only; the calibration was fitted on our own data.

## Licence and credits

Adapter, code and configuration: Apache-2.0 (LICENSE). Base: Qwen3.5-4B by the Qwen team (Apache-2.0). Prompt format:
SemIf by TheoLeeCJ (MIT). CUDA-graph runtime design and recipe shape: JevK5 by allebee (Apache-2.0). Evaluated with
JevBench by fstandhartinger (MIT). Not affiliated with TypeSafe AI or Jev. See NOTICE.md and EVALUATION-PERMISSION.md.