---
base_model: Qwen/Qwen3-VL-8B-Instruct
library_name: transformers
tags:
- sft
- trl
- radiology
- chest-xray
- medical-imaging
- report-generation
- mimic-cxr
license: apache-2.0
---

# Qwen3-VL-8B — MIMIC-CXR SFT

Fine-tuned version of [Qwen/Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) on a curated subset of the [MIMIC-CXR](https://physionet.org/content/mimic-cxr/2.0.0) dataset for radiology report generation and visual question answering on chest X-rays.

## How it was obtained

The model was trained with **supervised fine-tuning (SFT)** using [TRL](https://github.com/huggingface/trl). Training samples were selected from the MIMIC-CXR dataset, which contains frontal and lateral chest radiographs paired with structured radiology reports.

**Training details:**

| | |
|---|---|
| Base model | Qwen/Qwen3-VL-8B-Instruct |
| Training framework | TRL 0.26.2 (SFTTrainer) |
| Epochs | 2 |
| Total steps | 7 120 |
| Eval loss | 0.428 |
| Eval token accuracy | ~88% |
| Precision | bfloat16 |
| Hardware | 1× NVIDIA A100 |

## Usage

```python
from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "dmusingu/qwen3-vl-8b-mimic-cxr-sft",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
processor = AutoProcessor.from_pretrained("denmus/qwen3-vl-8b-mimic-cxr-sft")

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "<path_or_url_to_cxr>"},
            {"type": "text", "text": "Describe the findings in this chest X-ray."},
        ],
    }
]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(text=[text], images=image_inputs, return_tensors="pt").to(model.device)

output_ids = model.generate(**inputs, max_new_tokens=256)
output = processor.batch_decode(output_ids[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(output[0])
```

## Data access

MIMIC-CXR is a credentialed dataset. Access requires PhysioNet registration and completion of the required training at [physionet.org/content/mimic-cxr](https://physionet.org/content/mimic-cxr/2.0.0).

## Framework versions

- TRL: 0.26.2
- Transformers: 5.7.0
- PyTorch: 2.11.0
- Datasets: 4.8.4
- Tokenizers: 0.22.2

## Citation

If you use this model, please cite MIMIC-CXR:

```bibtex
@article{johnson2019mimic,
  title     = {MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports},
  author    = {Johnson, Alistair EW and Pollard, Tom J and Berkowitz, Seth J and others},
  journal   = {Scientific data},
  volume    = {6},
  number    = {1},
  pages     = {317},
  year      = {2019},
  publisher = {Nature Publishing Group}
}
```