---

license: other
license_name: s2-mas-controlled-research-v1.2
license_link: https://huggingface.co/ya9919/FinQ/blob/main/LICENSE

language:

- en

base_model: Qwen/Qwen3.5-4B-Base

tags:

- s2-mas

- financial-qa

- decision-head

- qwen3_5

- peft

- lora

---

# FinQ · Qwen3.5-4B-Base + LoRA + decision head · 200k QA

## Model naming and experiment labels

**FinQ — Qwen3.5-4B-Base + LoRA + learned decision head, 200k distinct QA** names this selected best checkpoint. [**FinL**](https://huggingface.co/ya9919/FinL) is the parallel full English-base six-round encoder route, and [**FinL-mlx**](https://huggingface.co/ya9919/FinL-mlx) is its MLX FP16 runtime. The original upstream model remains **Qwen/Qwen3.5-4B-Base**. Head-only, 50k and 9B Qwen checkpoints retain their explicit comparator names.

Paper: [S²-MAS](https://github.com/KataDavidXD/s2-mas/blob/main/paper/S2_MAS_Paper.pdf). The fixed-budget adaptation results and matched downstream methods define the comparison reported here.

## Project background

S²-MAS is a society-scale multi-agent simulation framework for studying how household decisions affect consumption, cash reserves and payments. The paper connects a constructed resource of **500 million household-persona records**, learned decision policies, reusable financial scenarios and a state-transition engine. Its purchase-funding application evaluates **12 million distinct synthetic household agents** under paired conditions. Full-data FinL supplies the policy for that application; this repository supplies a fixed-budget adaptation checkpoint for the common decision-model comparison. Decision learning uses **real-survey data**. The GENESE/MAS engine implementation remains private.

The benchmark groups twelve systems into six decision-model routes: encoder option scoring; language models with learned decision heads; next-token decision SFT; dynamic-schema classification; multimodal encoder decisions; and provider decision interfaces. All receive text inputs in the common benchmark. The **17 model-repository entries** comprise **10 fixed-budget trained variants**—five native Laya and five Qwen variants—plus **six checkpoint/runtime entries** and **one compatibility alias**.

## This model's role

**FinQ** follows the **language-model plus learned decision-head route**. LoRA adapters and a shared scalar decision head are trained together on Qwen3.5-4B-Base. The 200k head-only counterpart holds the backbone fixed, allowing the comparison to assess representation adaptation. The complete development partition selects this LoRA method before the separate 9B run.

## Training design and checkpoint

- Method: `lora`.

- Distinct downstream training rows: **200,000** from the fixed decision-QA training partition.

- Initialization: [Qwen/Qwen3.5-4B-Base](https://huggingface.co/Qwen/Qwen3.5-4B-Base).

- This stage terminal row exposures: **200,000**; selected checkpoint stage exposures: **200,000**.

- Selected checkpoint cumulative row exposures: **200,000**; selected cumulative distinct rows: **200,000**.

- A fixed 20,000-example development set selects this checkpoint. The complete 412,873-example development partition compares the two 200k Qwen4B adaptation methods.

## Performance and matched comparisons

**Language:** English. **Inference precision:** BF16 Qwen backbone with FP32 candidate scoring.

The common held-out test contains **240,458 QA records**, **119 question versions** and **8,275 respondent/household groups**. The checkpoint is selected using development data before this test.

| Checkpoint / reference | Accuracy (%) | Question-macro F1 (%) | Invalid decisions |
|---|---:|---:|---:|
| **FinQ · Qwen3.5-4B-Base + LoRA + head · 200k QA** | **74.1435** | **36.7343** | **0** |
| Qwen4B head only, same 200k unique QA | 67.2841 | 30.8995 | 0 |

Accuracy weights every test record equally; invalid decisions count as incorrect. Question-macro F1 averages over every defined candidate class within each question version and then weights the 119 versions equally.

The head-only reference uses the same pretrained backbone, unique examples and common test, with its backbone fixed. This checkpoint also adapts the backbone representation through LoRA.

## Package and inference

LoRA adapter plus a shared scalar decision head; obtain the official backbone separately.

The 4B initialization is the official pre-trained-only Base release.

- Model files: `head.pt, adapter/adapter_config.json, adapter/adapter_model.safetensors`.

- Reported common-test compute: BF16 Qwen backbone with FP32 candidate scoring.

- Obtain the official Qwen backbone and tokenizer named in the configuration separately.

- Inference scores the full state, question and complete candidate menu.

The supplied `qwen_decision.py` exposes the candidate-scoring inference interface. Supply the local package and the official backbone and tokenizer named in `decision_config.json`.

## License and access

The project model contribution is offered under the [S²-MAS Controlled Model Research License v1.2](LICENSE): noncommercial scientific use, no redistribution, and no unauthorized reverse engineering, extraction or distillation. Training and evaluation records are not distributed. Source-data access requires the provider's authorization. Permission requests: yli9919@hku.hk.

Project repository: [s2-mas](https://github.com/KataDavidXD/s2-mas).