---
license: apache-2.0
base_model: chaoliangUNSW/Jev-Style-2B-Decision-v3
base_model_relation: quantized
library_name: mlx
pipeline_tag: text-classification
tags:
- decision-model
- decision-making
- jev-style
- system-one
- calibration
- long-context
- qwen3.5
- mlx
- apple-silicon
- on-device
- llm-routing
- guardrails
---
# Jev-Style-2B-Decision-v3-MLX
**[Try it in your browser →](https://huggingface.co/spaces/chaoliangUNSW/jev-style-2b)**
**Website:** [jevstyle.com](https://jevstyle.com/#v3-2b) · **GitHub:** [jev-style](https://github.com/lawrence3699/jev-style) · **Collection:** [all v3 builds and demos](https://huggingface.co/collections/chaoliangUNSW/jev-style-decision-v3-08b-2b-6ab87f32380cbd8c03b608b9)
**Jev-Style decision series:** [v1 · 2B](https://huggingface.co/chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-MLX-bf16) → [v2 · 2B](https://huggingface.co/chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16) → [v3 · 0.8B](https://huggingface.co/chaoliangUNSW/Jev-Style-0.8B-Decision-v3-MLX) → **v3 · 2B**
**Jev-style decisions, now at 2B, native on Apple silicon.** These are the MLX builds of
[Jev-Style-2B-Decision-v3](https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v3): bf16 (3.76 GB) and
8-bit (2.00 GB) in one repository, with one runtime (`jev_style_decision_mlx.py`; choose the folder with `--model-dir bf16` or `--model-dir 8bit`). Full
results, protocols, training data and licences are on the
[main model card](https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v3).
| Public benchmark | **Jev-Style v3 · 2B** | Jev-Style v3 · 0.8B | Jev 1.13 (API) |
|---|:---:|:---:|:---:|
| JevBench v1.4.1, 231 public items ↑ | 73.6% | 64.1% | 86.6% |
| tweet_topic, zero-shot, accuracy ↑ | 82.2% | 75.5% | 79.3%¹ |
| fin_topic, zero-shot, accuracy ↑ | 61.1% | 46.7% | 67.0%¹ |
| Longest input per call | 25,600 tokens, no option cap | 25,600 tokens | |
Benchmark numbers of the model, measured with its GGUF F16 build (the pre-declared engine; one global temperature; each benchmark run once). The MLX builds were checked against the same FP32 reference (table below). JevBench: self-run with the official harness, not an official board entry; 95% CI 67.6–78.9% (Wilson). 73.6% is the highest JevBench public accuracy among the Qwen3.5-2B-family systems on the v1.4.1 board (decider-2b 71.0%, open-jev-zefan-2b 64.5%); decider-2b lies inside the CI. Jev is well ahead on JevBench and ahead on fin_topic. ¹ Jev numbers from the elcronos study (raw API), not re-run by us; on tweet_topic the 2B's macro-F1 (67.8%) is below Jev's (69.4%). Details: [main card](https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v3#results).
**25,600 tokens, no option cap.** State, questions and every option share one 25,600-token budget; question and
options over 2,048 tokens use a numbered-option catalogue. Nothing is truncated.
## Precisions and parity
| Precision | Folder | Weights | Same top-1 as PyTorch FP32 (1,000 rows) | Max abs Δp | Accuracy (FP32: 80.8%) | Long fixture (43 questions) | Gate |
|---|---|---:|---:|---:|---:|---:|:---:|
| **bf16** (default) | `bf16/` | 3.76 GB | **99.7%** | 0.035 | 80.5% | **43 / 43** | PASS |
| **8-bit** (affine, group size 64) | `8bit/` | 2.00 GB | **99.6%** | 0.162 | 80.8% | **43 / 43** | PASS |
- Each folder holds `model.safetensors`, its `config.json`, the tokenizer and `macjev_norms_fp32.safetensors`
(FP32 norm weights, 0.42 MB, required). The top level holds the shared runtime `jev_style_decision_mlx.py`,
`readout_config.json`, `release_config.json`, the sha256 `manifest.json`, `LICENSE`, `NOTICE`,
`THIRD_PARTY_NOTICES.md` and a copy of `bf16/config.json` (for the Hub's download counter). Converted with mlx
0.32.2 and mlx-lm 0.31.3.
- The 8-bit build makes the same call as full precision on 99.6% of the 1,000 rows at about half the size.
- **Which folder:** `bf16/` for closeness to the FP32 reference (max abs Δp 0.035 vs 0.162); `8bit/` when memory is
tight.
Reference: HF FP32 on CPU, exact block attention, on the released bf16 checkpoint; gates declared before any format was scored. 1,000 real development rows (≤4,096 tokens) test agreement between formats. Long fixture: 35 requests / 43 questions up to 25,600 tokens, including catalogue-overflow questions and up to 151 options. Sizes are the weight files (GB = 10^9 bytes).
## Speed
**Read once, then ask.** On an Apple M1 Max (MLX bf16), the first question about a 24,501-token input took 15.5 s; a further question about the same state took 0.15 s, because the state is computed once and reused (medians). Ten questions about that state in one call took 16.2 s.
| State | Questions per call | MLX bf16 | MLX 8-bit |
|---|---:|---:|---:|
| 878 tokens | 1 | 0.57 s | 0.72 s |
| 878 tokens | 10 | 1.07 s | 1.27 s |
| 3,950 tokens | 1 | 2.26 s | 2.96 s |
| 3,950 tokens | 10 | 2.80 s | 3.54 s |
| 24,436 tokens | 1 | 15.5 s | 19.9 s |
| 24,436 tokens | 10 | 16.2 s | 20.8 s |
| 24,436 tokens, already computed | 1 | 0.15 s | 0.16 s |
- Pick a precision folder by size and closeness to FP32 (Precisions table above). bf16 and 8-bit were timed one after another on the same shared machine; in these runs 8-bit was the slower folder in every row (indicative only).
Apple M1 Max, 64 GB, macOS 15.7.5. Wall time around one `decide` / `score_many` call (tokenisation included), median of 3 calls with the state recomputed each time; the model was loaded beforehand (loading took 3.1–3.7 s here, not included). States: English documentation and source code of 878, 3,950, 24,436 tokens plus the question; 10 questions = 4 choice, 4 true/false and 2 score questions about the same state in one call; with the question and options each input was up to 943, 4,015 and 24,501 tokens. MLX: mlx 0.32.2 / mlx-lm 0.31.3. Results were identical with and without a precomputed state. Other jobs shared the machine during these runs (1-minute load average 5.5–8.6 at the end of each run), so treat the numbers as indicative. All rows here were measured in one session (2026-09-27 03:21–03:28 AEST); an earlier run of the same rows (00:37–00:45 AEST, load average 11.8–27.5) was discarded because other jobs had slowed it (its times were up to 2.1× longer).
## Quick start
```bash
pip install -U huggingface_hub
hf download chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX --local-dir Jev-Style-2B-Decision-v3-MLX
cd Jev-Style-2B-Decision-v3-MLX
pip install -r requirements.txt # mlx 0.32.2, mlx-lm 0.31.3 (exactly), transformers 5.17.0, tokenizers, numpy
```
Only one precision is needed: add `--exclude "8bit/*"` to the download for bf16 only, or `--exclude "bf16/*"` for
8-bit only. Pass the precision folder to the runtime with `--model-dir bf16` or `--model-dir 8bit` (in Python,
`JevStyleDecisionMLX("bf16")` or `JevStyleDecisionMLX("8bit")`).
```bash
# choice question, bf16 weights
python jev_style_decision_mlx.py --model-dir bf16 --state "Finder is open on ~/Reports. The user asked: email report.pdf to Ana." \
--question "What should the agent do next?" \
--options '{"attach_report": "attach report.pdf to a new email to Ana", "rename_report": null, "close_finder": "close the Finder window"}'
# true/false question about a JSON state, 8-bit weights
python jev_style_decision_mlx.py --model-dir 8bit \
--state-json '{"app": "Mail", "draft": {"to": "ana@example.com", "attachments": []}}' \
--question "Is the report attached?" --qtype noul
# score (ordinal) question, uncalibrated probabilities (T = 1.0)
python jev_style_decision_mlx.py --model-dir 8bit --state "The deploy failed twice with the same migration error." \
--question "How risky is retrying now?" --qtype score --options '["no risk", "some risk", "high risk"]' --temperature 1.0
# full typed question as JSON, first checking the sha256 of the runtime files and the chosen precision folder (manifest.json)
python jev_style_decision_mlx.py --model-dir bf16 --verify --state "cart: 3 items" \
--question '{"t": "choice", "ins": "Next step?", "crit": {"checkout": null, "keep_shopping": null}}'
```
The output has `answer`, `probabilities` and raw `scores` per option, `temperature` (0.8279, the calibrated global
temperature), `top_probability`, `entropy_concentration`, `input_tokens`, `state_tokens`, `head_tokens`, `blocks`
and `catalogue_overflow`.
```python
from jev_style_decision_mlx import JevStyleDecisionMLX
m = JevStyleDecisionMLX("8bit") # the 8-bit precision folder
state = {"screen": "Settings > Wi-Fi", "goal": "join the network Office-5G"}
qs = [{"t": "choice", "ins": "Next action?", "crit": {"tap_office_5g": None, "toggle_wifi_off": None, "go_back": None}},
{"t": "noul", "ins": "Is Wi-Fi turned on?", "crit": None}]
for r in m.score_many(state, qs): # the state is computed once and reused for every question
print(r["answer"], round(r["top_probability"], 4))
m.decide(state, qs[0]) # same state again: reused (m.last_timing["state_reused"] is True)
m.close()
```
- Batch mode: `--jsonl requests.jsonl` (or `-` for stdin), rows `{"id"?, "state", "question", "options"?, "qtype"?,
"temperature"?}`; consecutive rows with an identical state share one state computation, and a malformed row gets
an `"error"` field while the batch continues.
- **Long inputs.** The complete input can be up to 25,600 tokens, with no separate question/options cap. In our
smoke test a 22,005-token state with 100 described options ran as 25,393 tokens in 14 blocks, using the
catalogue layout. A larger input raises `InputBudgetError` (CLI exit status 2); nothing is truncated.
- **mlx-lm must be exactly 0.31.3.** The runtime corrects two Qwen3.5 numerics inside mlx-lm and checks the source
it patches; other versions are refused with the install command. It also refuses to run without
`macjev_norms_fp32.safetensors` or `readout_config.json`, and never falls back to stock norms or T = 1.
- The input format, block attention and the readout are described on the
[main card](https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v3#input-format-and-readout).
## Scope and limits
- **Runtime required.** `mlx_lm.generate` can load the weights in `bf16/` or `8bit/` (the
repository root holds no weights) but still cannot produce the decision scores, and it would run causal attention.
Use `jev_style_decision_mlx.py`.
- **25,600 tokens** is the limit for the whole input (state + question + options + readout).
- **Reduced-data training.** The model was trained on a reduced data pool (60M tokens).
- **Decision Index.** Not run by us. The training pool includes the train splits of 7 of its benchmarks and
format-imitating data for 7 more, so results on these are not zero-shot; the 14 benchmarks that are not zero-shot
for this model are named on the [main card](https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v3#scope-and-limits).
Results charts
Protocol notes are under each chart and on the main card. Plotted values and sources: [jevbench.data.json](figures/jevbench.data.json), [zeroshot.data.json](figures/zeroshot.data.json).
## Disclaimers and licence
Apache-2.0. Built on Qwen/Qwen3.5-2B (Apache-2.0); `NOTICE` lists the modifications. Some training data has
restrictive or unclear terms (for example research-only jailbreak prompts and share-alike CC BY-SA sources), and some
training rows are outputs of OpenAI GPT and Anthropic Claude models, whose providers' terms of use may restrict how
models trained on them may be used. See [Training data and
licences](https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v3#training-data-and-licences) on the main card.
The runtime contains a modified copy of one mlx-lm 0.31.3 function (the Qwen3.5 `GatedDeltaNet.__call__`; MIT License,
Copyright Apple Inc.); its copyright and permission notice is in `THIRD_PARTY_NOTICES.md`. Not affiliated with,
endorsed by or connected to TypeSafe AI or Jev (no Jev weights, code or outputs are used), the Laya authors or the
Qwen team.
**AI disclosure:** code written with AI coding assistants (Claude Code) under my direction; I designed the project,
trained the models and verified the results.
## Contact
I welcome internship, employment, and research collaboration opportunities. Please contact me at [**yanchaoliang369@gmail.com**](mailto:yanchaoliang369@gmail.com).
欢迎提供实习、工作及科研合作机会，请邮件联系：[yanchaoliang369@gmail.com](mailto:yanchaoliang369@gmail.com)。