---
base_model: Qwen/Qwen3-VL-8B-Instruct
library_name: peft
pipeline_tag: image-text-to-text
tags:
- qwen3-vl
- lora
- causal-inference
- mm-vet
---

# CausalLens (Qwen3-VL-8B)

Weights for **CausalLens**: a Qwen3-VL-8B model with a LoRA adapter on the language model and a
*causal residual Q-Former* on the visual tokens. The Q-Former applies a backdoor-adjustment style
intervention over a fixed confounder dictionary and adds a small, gated residual to every visual
token before it enters the language model.

Code and usage: https://github.com/litcoderr/CausalLens

## Files

| Path | Content |
| --- | --- |
| `adapter_config.json`, `adapter_model.safetensors` | LoRA adapter (r=16, alpha=32; q/k/v/o/gate/up/down projections of the LLM) |
| `causal_qformer_adapter.pt`, `causal_qformer_config.json` | Causal residual Q-Former (weights + confounder dictionary 16384x256 + prior) |
| tokenizer / `preprocessor_config.json` / `chat_template.jinja` | Processor used for evaluation |
| `base/` | Qwen3-VL-8B base checkpoint that the adapters were trained on (fine-tuned from `Qwen/Qwen3-VL-8B-Instruct`, weights merged) |

## Usage

```bash
git clone https://github.com/litcoderr/CausalLens.git && cd CausalLens
./setup_env.sh                  # Python 3.11 venv with pinned dependencies
./download.sh                   # this repository -> checkpoints/CausalLens (base -> checkpoints/CausalLens/base)
./run_mmvet.sh                  # MM-Vet inference (data setup: see the GitHub README)
```

From Python (inside the CausalLens repository):

```python
from causallens import load_model_and_processor

model, processor = load_model_and_processor(
    base_model="checkpoints/CausalLens/base",
    checkpoint="checkpoints/CausalLens",
)
```