---
base_model: Qwen/Qwen3-VL-8B-Instruct
library_name: transformers
model_name: Qwen3-VL-8B-german-shorthand
tags:
- generated_from_trainer
- sft
- trl
- vision-language
- ocr
- transcription
- medieval
- german
- shorthand
licence: license
---

# Model Card for Qwen3-VL-8B-german-shorthand

This model is a fine-tuned version of [Qwen/Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) for transcribing medieval German shorthand from images.
It has been trained using [TRL](https://github.com/huggingface/trl) on the [wjbmattingly/german-shorthand-window-5-4](https://huggingface.co/datasets/wjbmattingly/medieval-data-german-shorthand-window-5-4) dataset.

## Model Description

This vision-language model specializes in transcribing text from images of German shorthand documents. Given an image of shorthand text, the model generates the corresponding transcription.

## Quick start

```python
from transformers import AutoProcessor, Qwen3VLForConditionalGeneration
from peft import PeftModel
from PIL import Image

# Load model and processor
base_model = "Qwen/Qwen3-VL-8B-Instruct"
adapter_model = "wjbmattingly/Qwen3-VL-8B-german-shorthand"

model = Qwen3VLForConditionalGeneration.from_pretrained(
    base_model,
    torch_dtype="auto",
    device_map="auto"
)
model = PeftModel.from_pretrained(model, adapter_model)
processor = AutoProcessor.from_pretrained(base_model)

# Load your image
image = Image.open("path/to/your/shorthand_image.jpg")

# Prepare the message
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image},
            {"type": "text", "text": "Transcribe the text shown in this image."},
        ],
    },
]

# Generate transcription
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device)

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
transcription = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]

print(transcription)
```

## Training procedure

This model was fine-tuned using Supervised Fine-Tuning (SFT) with LoRA adapters on the Qwen3-VL-8B-Instruct base model.

### Training Data

The model was trained on [wjbmattingly/german-shorthand-window-5-4](https://huggingface.co/datasets/wjbmattingly/german-shorthand-window-5-4), 
a dataset containing images of German shorthand with corresponding text transcriptions.

### Training Configuration

- **Base Model**: Qwen/Qwen3-VL-8B-Instruct
- **Training Method**: Supervised Fine-Tuning (SFT) with LoRA
- **LoRA Configuration**:
  - Rank (r): 16
  - Alpha: 32
  - Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
  - Dropout: 0.1
- **Training Arguments**:
  - Epochs: 3
  - Batch size per device: 2
  - Gradient accumulation steps: 4
  - Learning rate: 5e-5
  - Optimizer: AdamW
  - Mixed precision: FP16

### Framework versions

- TRL: 0.23.0
- Transformers: 4.57.1
- Pytorch: 2.8.0
- Datasets: 4.1.1
- Tokenizers: 0.22.1

## Citations



Cite TRL as:
    
```bibtex
@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}
```