---
library_name: peft
pipeline_tag: image-text-to-text
base_model: Qwen/Qwen2.5-VL-7B-Instruct
tags:
- image-forensics
- forgery-detection
- qwen2.5-vl
- lora
- peft
- so-fake-r1
---

# So-Fake-R1 Model Weights

This repository contains the model weights used by So-Fake-R1, an evidence-grounded framework for social-media image forgery detection.

The Qwen2.5-VL-7B-Instruct base model is not redistributed here. The released VLM components are LoRA adapters that should be loaded with `Qwen/Qwen2.5-VL-7B-Instruct`.

## Contents

```text
observer_adapter/          Visual Observer LoRA adapter
decision_maker_adapter/    Decision Maker LoRA adapter
provider/                  Forensic Evidence Provider checkpoints
model_manifest.json        Component manifest
SHA256SUMS                 File checksums
```

The provider directory contains four small checkpoints:

```text
npr_internalized_feta_mono_blur_only05_e1.pt
feta_v0_L19_cls_only10d_L19_u1_e1.pt
npr_feta_cls_npr_residual_feta10d_e1.pt
l19_heatmap_bbox_head_best.pt
```

## Expected Use

These weights are intended to be used with the So-Fake-R1 inference code. A typical runtime uses:

```bash
export QWEN_BASE_MODEL=Qwen/Qwen2.5-VL-7B-Instruct
export SOFAKE_R1_OBSERVER_ADAPTER=/path/to/observer_adapter
export SOFAKE_R1_DM_CKPT=/path/to/decision_maker_adapter
export SOFAKE_R1_PROVIDER_DIR=/path/to/provider
```

SAM2 is only required when exporting SAM2-refined masks from predicted boxes.

## Notes

- Optimizer states, scheduler states, and training logs are intentionally excluded.
- The observer is released as a LoRA adapter rather than a merged full Qwen checkpoint.
- The Decision Maker is the v5.64 route-aware GRPO checkpoint.