BehaviorTune QLoRA Adapter
QLoRA adapter for Qwen/Qwen3-4B-Instruct-2507, trained on the 240-row BehaviorTune training split and evaluated with matched BASE / SYSTEM / CONTEXT / QLoRA conditions.
What this demonstrates
- Open-model post-training with Transformers, TRL, PEFT, and QLoRA.
- Completion-only training on a controlled synthetic dataset.
- Deterministic matched evaluation against the untuned base model.
- Public adapter, dataset, results, and reproducible engineering tooling.
Measured result
On the frozen eval_core set, QLoRA increased format-valid activation from 0.65625 to 1.00000 — a +0.34375 (+34.375 percentage-point) matched shift, with a paired-bootstrap 95% CI of [0.1875, 0.5].
Training
| Item | Value |
|---|---|
| Base model | Qwen/Qwen3-4B-Instruct-2507 |
| Base revision | cdbee75f17c01a7cc42f958dc650907174af0554 |
| Training rows | 240 |
| Epochs | 3 |
| Optimizer steps | 90 |
| Quantization | 4-bit NF4, BF16 compute |
| LoRA | rank 32, alpha 64, dropout 0.05, all linear projections |
| Effective batch size | 8 |
| Learning rate | 0.0002 |
| Seed | 147 |
| Hardware | NVIDIA A100-SXM4-40GB |
Project resources
- BehaviorTune on GitHub
- BehaviorTune dataset
- Results and limitations
- Engineering quickstart
- Evidence map
Artifact identity
- Adapter SHA-256:
8d16ef2cb6ff7a982511fd58f21eff52538761f4d198b4cc5cbfd73ca7c9d4de - Frozen run identifier:
V1.1-R1 - Public release: BehaviorTune v1.0.0
Use and limitations
Load the pinned base revision and attach this PEFT adapter.
The measured result is limited to the frozen eval_core evaluation under BASE, SYSTEM, CONTEXT, and QLoRA. It does not establish results for holdouts, LONG-NEUTRAL, persistence, remediation, or other model families.
license: other applies to this adapter repository. The upstream base model remains governed by its own license.
- Downloads last month
- 54
Model tree for aamish-ahmad/behaviortune-v1-1-r1-adapter
Base model
Qwen/Qwen3-4B-Instruct-2507