rect2sheet-qwen-7b

Rect2Sheet Qwen 7B

<img width="3805" height="1383" alt="Rect2Sheet dataset overview" src="https://github.com/user-attachments/assets/0162d15f-6358-478a-a0aa-285fa3c4343b" />

Rect2Sheet Qwen 7B is a fine-tuned version of unsloth/qwen2.5-coder-7b-instruct for generating sheet-metal solutions from rectangle layouts. Given a JSON description of connected rectangular tabs, the model produces a candidate solution containing the fold sequence, bends, bend directions, and resulting tab geometry.

The model was trained on the manually verified release of the Rect2Sheet dataset, which contains 19,231 synthetic sheet-metal designs. The dataset was generated with SheetGen and is archived on Zenodo.

Model Details

Usage

The prompt should contain one complete Rect2Sheet rectangle JSON object. Explicitly request only the solution JSON so the response can be parsed directly.

import json

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "atsmt/rect2sheet-qwen-7b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

with open("001_rectangle.json", encoding="utf-8") as file:
    rectangle = json.load(file)

messages = [
    {
        "role": "user",
        "content": (
            "Generate a Rect2Sheet sheet-metal solution for the following rectangle layout. "
            "Return only valid solution JSON.\n\n"
            + json.dumps(rectangle)
        ),
    }
]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.inference_mode():
    output = model.generate(**inputs, max_new_tokens=4096, do_sample=False)

generated = output[0, inputs.input_ids.shape[1]:]
print(tokenizer.decode(generated, skip_special_tokens=True))

Example rectangle and solution files are available in the repository's dataset_test_1/dataset_json directory.

llama.cpp

Quantized GGUF files are included in the model repository and can be run directly:

llama-cli -hf atsmt/rect2sheet-qwen-7b --jinja

Intended Use

This model is intended for research into data-driven sheet-metal design generation and for producing candidate Rect2Sheet solutions from inputs that follow the dataset schema. It may also be useful as a baseline for constrained CAD generation and geometry-generation research.

Limitations

• Generated JSON may be malformed or may not conform to the Rect2Sheet schema.
• A syntactically valid output is not necessarily geometrically valid or manufacturable.
• The model does not replace collision, unfolding-overlap, thin-segment, or other engineering checks.
• Performance outside the tab counts, geometry, mount types, and topology represented in the training data is unknown.
• No benchmark results are currently reported for this release.

Validate every generated design with geometry and manufacturability tooling, such as the SheetGen pipeline, before using it in downstream engineering or fabrication workflows.

Dataset

Rect2Sheet pairs rectangle layouts with sheet-metal solutions. Inputs describe tabs through corner points A, B, and C, with optional mounts. Targets describe the fold sequence, bends with tab and point references, bend direction, and the resulting tab geometry. The accepted solutions were filtered for manufacturability and manually inspected. See the dataset repository for the schema, test subsets, and generation details.

Citation

Please cite the Rect2Sheet dataset and SheetGen when using this model:

@dataset{tender2026rect2sheet,
  author    = {Tender, A. M. and Wittig Adão, C. and Matthiesen, S.},
  title     = {Rect2Sheet: A Dataset of Sheet Metal Connection Designs},
  year      = {2026},
  publisher = {Karlsruhe Institute of Technology},
  doi       = {10.5281/zenodo.20834240},
  url       = {https://doi.org/10.5281/zenodo.20834240}
}

License

This model is released under the Apache License 2.0. The Rect2Sheet dataset and upstream model may have their own terms; review them before use.